Learning Objects

This tutorial aims to introduce basic ways to preprocess data before we model data using R. We will cover:

  1. Basic intro to R

  2. How to read, clean, and transform text data

  3. How to preprocess data such as tokenization, removing stop words, lemmatization, stemming, and representing words in R

  4. How to get basic statistics from texts using lexicon methods

In the first part of python tutorial, we have covered some basic things about how to read and save files in Python, how to recognize regEx, and how to use selenium to do webscraping.

We were able to successfully scrape the BLM protest events dataset. You can access the dataset https://yongjunzhang.com/files/tutorial/blm-data.tsv

Here is our lab training problem set:

  1. You need to submit a script showing you are able to run the selenium and actually gather the data
  2. You need to scrape the original news articles using “blm-data.tsv” dataset (it has source urls) and make a structured textual data set.
  3. If you want to earn these extra credits, you need to turn in your scripts and dataset before Sept 8th, 6:00 PM via email.

Lab 2 Part 2. Basic Intro to R and Preprossing Textual Data with R

We need to load some packages for use

if (!requireNamespace("pacman"))
  install.packages('pacman')
## Loading required namespace: pacman
library(pacman)
packages<-c("tidyverse","tidytext","rvest", "RSelenium",
            "tm","haven","readxl","here","knitr","stopwords")
p_load(packages,character.only = TRUE)

Load blm-data tsv file

R tidyverse package provides a series of useful data wrangling tools. You can check it here https://www.tidyverse.org/. The tidyverse package installs a number of other packages for reading data:

  1. DBI for relational databases. You’ll need to pair DBI with a database specific backends like RSQLite, RMariaDB, RPostgres, or odbc. Learn more at https://db.rstudio.com.

  2. haven for SPSS, Stata, and SAS data.

  3. httr for web APIs.

  4. readxl for .xls and .xlsx sheets.

  5. rvest for web scraping.

  6. jsonlite for JSON. (Maintained by Jeroen Ooms.)

  7. xml2 for XML.

# read tsv file using read_csv
data <- read_tsv(url("https://yongjunzhang.com/files/tutorial/blm-data.tsv"))
## Parsed with column specification:
## cols(
##   page_id = col_double(),
##   protest_id = col_double(),
##   protest_location = col_character(),
##   protest_start = col_character(),
##   protest_end = col_character(),
##   protest_subject = col_character(),
##   protest_participants = col_character(),
##   protest_time = col_character(),
##   protest_description = col_character(),
##   protest_urls = col_character()
## )
# Show a table for visual check
knitr::kable(data[1:3,],cap="Black Lives Matter Protest (elephrame.com)")
Black Lives Matter Protest (elephrame.com)
page_id protest_id protest_location protest_start protest_end protest_subject protest_participants protest_time protest_description protest_urls
1 4669 Louisville, KY Monday, July 20, 2020 - Present Subject(s): Breonna Taylor, Sgt. Jonathan Mattingly, Ofc. Brett Hankison, Ofc. Myles Cosgrov Participant(s): 4 Time: Continuous Description: Hunger strike for firing of & stripping pensions from officers who killed Taylor Source(s):##https://www.facebook.com/hungerstrikersforbreonna/videos/288546628879982/##(livestream##of##strike)##https://www.courier-journal.com/story/news/local/2020/07/19/louisville-protests-hunger-strike-for-breonna-taylor-livestream/5467930002/##https://www.courier-journal.com/story/news/politics/metro-government/2020/05/16/breonna-taylor-shooting-what-we-know-louisville-police-officers-involved/5200879002/
1 4640 Washington, DC Friday, May 29, 2020 - Present Subject(s): General - Police Brutality, General - Racism/White Supremacy, General - Trump Administration Participant(s): Thousands Time: Continuous Description: Near constant presence of demonstrators and/or displays of protest signs near White House, Lafayette Square & BLM Plaza Source(s):##https://www.washingtonpost.com/local/dc-black-lives-matter-plaza-transformed/2020/07/20/641a1f50-c52e-11ea-8ffe-372be8d82298_story.html##https://www.washingtonpost.com/local/in-lafayette-square-visitors-return-to-a-park-changed-by-protests/2020/06/11/5ad564be-ac00-11ea-a9d9-a81c1a491c52_story.html##https://www.fox5dc.com/news/massive-fence-erected-around-lafayette-park-becomes-gallery-of-protest-art
1 4538 Minneapolis, MN Friday, June 5, 2020 - Present Subject(s): General - Police Brutality Participant(s): 15 Time: Continuous Description: “Say Their Names” mock cemetery of people killed by police Source(s):##https://theconversation.com/black-deaths-matter-the-centuries-old-struggle-to-memorialize-slaves-and-victims-of-racism-140613##https://www.mndaily.com/article/2020/06/say-their-names-cemetery##https://twitter.com/TwinCityReports/status/1272286571929178112##https://twitter.com/TwinCityReports/status/1272718480148660224

Clean blm-data

Let us say, we need to create variables like state and city; we also want to clean some variables like subjects, description, etc.

data <- data %>% 
  # split location
  separate(protest_location,c("city","state"),sep = ",",remove = T) %>% 
  # split protest start time
  separate(protest_start,c("day","date","year"),sep = ",",remove = T) %>%
  # clean subjects and participants
  mutate(
    protest_subject = str_replace(protest_subject,"Subject\\(s\\): ",""),
    protest_participants = str_replace(protest_participants,"Participant\\(s\\): ",""),
    protest_time = str_replace(protest_time,"Time: ",""),
    protest_description = str_replace(protest_description,"Description: ",""),
    protest_urls = str_replace(protest_urls,"Source\\(s\\):","")
    )
## Warning: Expected 2 pieces. Additional pieces discarded in 464 rows [12, 111,
## 147, 272, 273, 278, 339, 393, 394, 422, 436, 450, 499, 500, 519, 527, 532, 545,
## 568, 583, ...].
## Warning: Expected 2 pieces. Missing pieces filled with `NA` in 17 rows [220,
## 329, 354, 358, 1045, 2196, 2525, 4098, 4211, 4305, 4390, 4434, 4451, 4455, 4475,
## 4480, 4578].
# Show a table for visual check
knitr::kable(data[1:3,],cap="Black Lives Matter Protest (elephrame.com)")
Black Lives Matter Protest (elephrame.com)
page_id protest_id city state day date year protest_end protest_subject protest_participants protest_time protest_description protest_urls
1 4669 Louisville KY Monday July 20 2020 - Present Breonna Taylor, Sgt. Jonathan Mattingly, Ofc. Brett Hankison, Ofc. Myles Cosgrov 4 Continuous Hunger strike for firing of & stripping pensions from officers who killed Taylor ##https://www.facebook.com/hungerstrikersforbreonna/videos/288546628879982/##(livestream##of##strike)##https://www.courier-journal.com/story/news/local/2020/07/19/louisville-protests-hunger-strike-for-breonna-taylor-livestream/5467930002/##https://www.courier-journal.com/story/news/politics/metro-government/2020/05/16/breonna-taylor-shooting-what-we-know-louisville-police-officers-involved/5200879002/
1 4640 Washington DC Friday May 29 2020 - Present General - Police Brutality, General - Racism/White Supremacy, General - Trump Administration Thousands Continuous Near constant presence of demonstrators and/or displays of protest signs near White House, Lafayette Square & BLM Plaza ##https://www.washingtonpost.com/local/dc-black-lives-matter-plaza-transformed/2020/07/20/641a1f50-c52e-11ea-8ffe-372be8d82298_story.html##https://www.washingtonpost.com/local/in-lafayette-square-visitors-return-to-a-park-changed-by-protests/2020/06/11/5ad564be-ac00-11ea-a9d9-a81c1a491c52_story.html##https://www.fox5dc.com/news/massive-fence-erected-around-lafayette-park-becomes-gallery-of-protest-art
1 4538 Minneapolis MN Friday June 5 2020 - Present General - Police Brutality 15 Continuous “Say Their Names” mock cemetery of people killed by police ##https://theconversation.com/black-deaths-matter-the-centuries-old-struggle-to-memorialize-slaves-and-victims-of-racism-140613##https://www.mndaily.com/article/2020/06/say-their-names-cemetery##https://twitter.com/TwinCityReports/status/1272286571929178112##https://twitter.com/TwinCityReports/status/1272718480148660224

Using Tidytest package to process some variables

There are a variety of processing text packages. Today we briefly introduce tidytext package. You can check herehttps://cran.r-project.org/web/packages/tidytext/vignettes/tidytext.html; This tidytext toturial heavily relies on Julia Silge and David Robinson’s work. You can also check their book Text Mining with R here https://www.tidytextmining.com/

library(tidytext)

# Let us say we are interested in protest description. We need to restructure it as one-token-per-row format. The unnest_tokens function is a way to convert a dataframe with a text column to be one-token-per-row:

tidy_data <- data %>%
  # protest_urls is messay, let us get rid of it first
  select(-protest_urls) %>% 
  # one token per row. This function uses the tokenizers package to separate each line into words. The default tokenizing is for words, but other options include characters, ngrams, sentences, lines, paragraphs, or separation around a regex pattern.
  unnest_tokens(word, protest_description) %>% 
  # remove stop words
  anti_join(tidytext::get_stopwords("en",source="snowball")) %>% 
  # you can also add your own stop words if you want
  # check here to see tibble data structure <https://tibble.tidyverse.org/>
  anti_join(tibble(word=c("no","details")),by="word")
## Joining, by = "word"
knitr::kable(tidy_data[1:10,],cap="Black Lives Matter Protest (elephrame.com)")
Black Lives Matter Protest (elephrame.com)
page_id protest_id city state day date year protest_end protest_subject protest_participants protest_time word
1 4669 Louisville KY Monday July 20 2020 - Present Breonna Taylor, Sgt. Jonathan Mattingly, Ofc. Brett Hankison, Ofc. Myles Cosgrov 4 Continuous hunger
1 4669 Louisville KY Monday July 20 2020 - Present Breonna Taylor, Sgt. Jonathan Mattingly, Ofc. Brett Hankison, Ofc. Myles Cosgrov 4 Continuous strike
1 4669 Louisville KY Monday July 20 2020 - Present Breonna Taylor, Sgt. Jonathan Mattingly, Ofc. Brett Hankison, Ofc. Myles Cosgrov 4 Continuous firing
1 4669 Louisville KY Monday July 20 2020 - Present Breonna Taylor, Sgt. Jonathan Mattingly, Ofc. Brett Hankison, Ofc. Myles Cosgrov 4 Continuous stripping
1 4669 Louisville KY Monday July 20 2020 - Present Breonna Taylor, Sgt. Jonathan Mattingly, Ofc. Brett Hankison, Ofc. Myles Cosgrov 4 Continuous pensions
1 4669 Louisville KY Monday July 20 2020 - Present Breonna Taylor, Sgt. Jonathan Mattingly, Ofc. Brett Hankison, Ofc. Myles Cosgrov 4 Continuous officers
1 4669 Louisville KY Monday July 20 2020 - Present Breonna Taylor, Sgt. Jonathan Mattingly, Ofc. Brett Hankison, Ofc. Myles Cosgrov 4 Continuous killed
1 4669 Louisville KY Monday July 20 2020 - Present Breonna Taylor, Sgt. Jonathan Mattingly, Ofc. Brett Hankison, Ofc. Myles Cosgrov 4 Continuous taylor
1 4640 Washington DC Friday May 29 2020 - Present General - Police Brutality, General - Racism/White Supremacy, General - Trump Administration Thousands Continuous near
1 4640 Washington DC Friday May 29 2020 - Present General - Police Brutality, General - Racism/White Supremacy, General - Trump Administration Thousands Continuous constant
# let us see what stopwords we are excluding
stopwords_d <- tidytext::get_stopwords()
stopwords_d$word
##   [1] "i"          "me"         "my"         "myself"     "we"        
##   [6] "our"        "ours"       "ourselves"  "you"        "your"      
##  [11] "yours"      "yourself"   "yourselves" "he"         "him"       
##  [16] "his"        "himself"    "she"        "her"        "hers"      
##  [21] "herself"    "it"         "its"        "itself"     "they"      
##  [26] "them"       "their"      "theirs"     "themselves" "what"      
##  [31] "which"      "who"        "whom"       "this"       "that"      
##  [36] "these"      "those"      "am"         "is"         "are"       
##  [41] "was"        "were"       "be"         "been"       "being"     
##  [46] "have"       "has"        "had"        "having"     "do"        
##  [51] "does"       "did"        "doing"      "would"      "should"    
##  [56] "could"      "ought"      "i'm"        "you're"     "he's"      
##  [61] "she's"      "it's"       "we're"      "they're"    "i've"      
##  [66] "you've"     "we've"      "they've"    "i'd"        "you'd"     
##  [71] "he'd"       "she'd"      "we'd"       "they'd"     "i'll"      
##  [76] "you'll"     "he'll"      "she'll"     "we'll"      "they'll"   
##  [81] "isn't"      "aren't"     "wasn't"     "weren't"    "hasn't"    
##  [86] "haven't"    "hadn't"     "doesn't"    "don't"      "didn't"    
##  [91] "won't"      "wouldn't"   "shan't"     "shouldn't"  "can't"     
##  [96] "cannot"     "couldn't"   "mustn't"    "let's"      "that's"    
## [101] "who's"      "what's"     "here's"     "there's"    "when's"    
## [106] "where's"    "why's"      "how's"      "a"          "an"        
## [111] "the"        "and"        "but"        "if"         "or"        
## [116] "because"    "as"         "until"      "while"      "of"        
## [121] "at"         "by"         "for"        "with"       "about"     
## [126] "against"    "between"    "into"       "through"    "during"    
## [131] "before"     "after"      "above"      "below"      "to"        
## [136] "from"       "up"         "down"       "in"         "out"       
## [141] "on"         "off"        "over"       "under"      "again"     
## [146] "further"    "then"       "once"       "here"       "there"     
## [151] "when"       "where"      "why"        "how"        "all"       
## [156] "any"        "both"       "each"       "few"        "more"      
## [161] "most"       "other"      "some"       "such"       "no"        
## [166] "nor"        "not"        "only"       "own"        "same"      
## [171] "so"         "than"       "too"        "very"       "will"

Part 3. Basic Analysis of Textual Data

Let us get a count vector for protest description, like what are the most frequent words or bi-grams

tidy_data %>% 
  count(word, sort = TRUE) 
## # A tibble: 3,826 x 2
##    word              n
##    <chr>         <int>
##  1 demonstration  1356
##  2 included       1330
##  3 march           975
##  4 rally           839
##  5 outside         466
##  6 national        424
##  7 game            423
##  8 anthem          418
##  9 police          379
## 10 prior           379
## # … with 3,816 more rows

We can further plot this! I don’t like wordcloud, so I just do a simple bar plot.

library(ggplot2)

tidy_data %>%
  count(word, sort = TRUE) %>%
  filter(n > 100) %>%
  mutate(word = reorder(word, n)) %>%
  ggplot(aes(word, n)) +
  geom_col() +
  xlab(NULL) +
  coord_flip()

let us get bigram

 data %>%
  select(-protest_urls) %>% 
  unnest_tokens(bigram, protest_description,token = "ngrams", n = 2) %>%
  count(bigram,sort = TRUE)
## # A tibble: 11,401 x 2
##    bigram                 n
##    <chr>              <int>
##  1 for this            1333
##  2 no details          1333
##  3 this demonstration  1322
##  4 details included    1321
##  5 included for        1321
##  6 national anthem      400
##  7 prior to             379
##  8 during national      376
##  9 anthem prior         363
## 10 nfl game             235
## # … with 11,391 more rows

Note you can use joining functions to filter these words or ngrams… such as inner_join, anti_join, semi_join, etc.

We can also use tidytext to build document-term matrix or tf-idf. We will cover this next time when we talk about topic modeling.

In the lecture, we briefly mentioned how we represent text in NLP. In Text as Data, the authors mainly summarized the approach of “bag of words” (CoW). It is just one approach to quantify what a document is about. How important a word may be in your document or in the entire corpus (collection of documents)?

One measure of the importance of a word is its term frequency (tf). It captures the frequency of a word in a document. There are very frequent words in a document but may not be important; in English, some stopwords, like “the”, “is”, “of”, “and”, etc. So we need to remove them before analysis based on your research. But for other scholar’s that might be of their interest.

Another way is to look at a term’s inverse document frequency (idf), which decreases the weight for commonly used words and increases the weight for words that are not used very much in a collection of documents.

This can be combined with term frequency to calculate a term’s tf-idf (the two quantities multiplied together), the frequency of a term adjusted for how rarely it is used.

You can check text mining with R book here https://www.tidytextmining.com/tfidf.html#tfidf

tidy_words <- tidy_data %>%
  count(protest_id, word, sort = TRUE)

tidy_words
## # A tibble: 24,521 x 3
##    protest_id word        n
##         <dbl> <chr>   <int>
##  1       2414 march       4
##  2       1370 square      3
##  3       2767 city        3
##  4       4501 center      3
##  5       4753 workers     3
##  6         11 w           2
##  7        204 die         2
##  8        262 police      2
##  9        303 street      2
## 10        322 march       2
## # … with 24,511 more rows

The idea of tf-idf is to find the important words for the content of each document by decreasing the weight for commonly used words and increasing the weight for words that are not used very much in a collection or corpus of documents.

The bind_tf_idf function in the tidytext package takes a tidy text dataset as input with one row per token (term), per document. One column (word here) contains the terms/tokens, one column contains the documents (book in this case), and the last necessary column contains the counts, how many times each document contains each term.

tidy_words <- tidy_words %>%
  bind_tf_idf(word, protest_id, n)

tidy_words
## # A tibble: 24,521 x 6
##    protest_id word        n    tf   idf tf_idf
##         <dbl> <chr>   <int> <dbl> <dbl>  <dbl>
##  1       2414 march       4 0.222  1.58  0.351
##  2       1370 square      3 0.188  4.11  0.771
##  3       2767 city        3 0.188  2.88  0.540
##  4       4501 center      3 0.25   4.01  1.00 
##  5       4753 workers     3 0.231  4.13  0.953
##  6         11 w           2 0.182  3.70  0.674
##  7        204 die         2 0.286  3.93  1.12 
##  8        262 police      2 0.143  2.53  0.362
##  9        303 street      2 0.167  4.32  0.720
## 10        322 march       2 0.2    1.58  0.316
## # … with 24,511 more rows

Let us take a look at those relatively important words

tidy_words %>%
  arrange(desc(tf_idf)) %>%
  mutate(word = factor(word, levels = rev(unique(word)))) %>% 
  group_by(protest_id) %>% 
  filter(protest_id%in%sample(2000:5000, 4, replace=F)) %>% 
  top_n(10) %>% 
  ungroup() %>%
  ggplot(aes(word, tf_idf, fill = protest_id)) +
  geom_col(show.legend = FALSE) +
  labs(x = NULL, y = "tf-idf") +
  facet_wrap(~protest_id, ncol = 2, scales = "free") +
  coord_flip()
## Selecting by tf_idf

Part 4. Use Stanford CoreNLP Package to do basic text processing

Check here for CORENLPhttps://stanfordnlp.github.io/CoreNLP/other-languages.html

CoreNLP enables users to derive linguistic annotations for text, including token and sentence boundaries, parts of speech, named entities, numeric and time values, dependency and constituency parses, coreference, sentiment, quote attributions, and relations. CoreNLP currently supports 6 languages, including Arabic, Chinese, English, French, German, and Spanish. https://stanfordnlp.github.io/CoreNLP/index.html

Let us say we want to go deeper about BLM data. The BLM-DATA.TSV provides the original protest urls (news articles). We want to process those original articles to get more info.

Let us use httr or rvest to scrape a couple of news articles for example.

# create a dataset having urls, year, and ids
urls <- data %>% 
  select(protest_id,state,date,protest_urls) %>% 
  # let us extract all protest_urls
  mutate(protest_urls=str_replace_all(protest_urls,"^##|^#","")) %>% 
  separate_rows(protest_urls,sep="##") %>% 
  filter(str_detect(protest_urls,"^http"))

# only keep one url for each protest
urls1 <- urls %>% 
  distinct(protest_id,.keep_all = T)

# let us take a look at the data
knitr::kable(urls1[1:5,],cap="Black Lives Matter Protest (elephrame.com)")
Black Lives Matter Protest (elephrame.com)
protest_id state date protest_urls
4669 KY July 20 https://www.facebook.com/hungerstrikersforbreonna/videos/288546628879982/
4640 DC May 29 https://www.washingtonpost.com/local/dc-black-lives-matter-plaza-transformed/2020/07/20/641a1f50-c52e-11ea-8ffe-372be8d82298_story.html
4538 MN June 5 https://theconversation.com/black-deaths-matter-the-centuries-old-struggle-to-memorialize-slaves-and-victims-of-racism-140613
4522 NC July 9 https://www.wral.com/fayetteville-mayor-says-protesters-must-move-from-market-house/19186797/
3937 KY June 5 https://twitter.com/HayesGardner/status/1273370970686984199

Use httr and rvest packages to get access to articles. Note that a lot of news articles need speciall subsription to get access such as facebook, wp, etc.

rvest and httr have a lot of functions. here is an overview (credit to GITHUB:yusuzech)

knitr::include_graphics('rvest_httr.png')

library(rvest)
library(httr)
## 
## Attaching package: 'httr'
## The following object is masked from 'package:NLP':
## 
##     content
url <- urls1$protest_urls[4]
url
## [1] "https://www.wral.com/fayetteville-mayor-says-protesters-must-move-from-market-house/19186797/"
# rvest provides two ways of making request: read_html() and html_session() 
# read_html() can parse a HTML file or an url into xml document. 
# html_session() is built on GET() from httr package.

#making GET request andparse website into xml document
pagesource <- read_html(url)

#using html_session which creates a session and accept httr methods
my_session <- html_session(url)

#html_session is built upon httr, you can access response with a session
response <- my_session$response

#retrieve content as raw
content_raw <- content(my_session$response,as = "raw")
#retrieve content as text
content_text <- content(my_session$response,as = "text")
#retrieve content as parsed(parsed automatically)
content_parsed <- content(my_session$response,as = "parsed")

Obviously it returns a bunch of messy stuff; You need to use RSelenium to scrape these dynamic websites; we have learnt basic Selenium stuff in python. You can read this turorial for more details https://ropensci.org/tutorials/rselenium_tutorial/

Here let me briefly show you we can also do this in R

# connect to chrome driver
driver <- RSelenium::rsDriver(browser = "chrome")
## checking Selenium Server versions:
## BEGIN: PREDOWNLOAD
## BEGIN: DOWNLOAD
## BEGIN: POSTDOWNLOAD
## checking chromedriver versions:
## BEGIN: PREDOWNLOAD
## BEGIN: DOWNLOAD
## BEGIN: POSTDOWNLOAD
## checking geckodriver versions:
## BEGIN: PREDOWNLOAD
## BEGIN: DOWNLOAD
## BEGIN: POSTDOWNLOAD
## checking phantomjs versions:
## BEGIN: PREDOWNLOAD
## BEGIN: DOWNLOAD
## BEGIN: POSTDOWNLOAD
## [1] "Connecting to remote server"
## $acceptInsecureCerts
## [1] FALSE
## 
## $browserName
## [1] "chrome"
## 
## $browserVersion
## [1] "85.0.4183.83"
## 
## $chrome
## $chrome$chromedriverVersion
## [1] "85.0.4183.87 (cd6713ebf92fa1cacc0f1a598df280093af0c5d7-refs/branch-heads/4183@{#1689})"
## 
## $chrome$userDataDir
## [1] "/var/folders/wv/yqy4jphx1hlbmxfqd2zrrcbr0000gn/T/.com.google.Chrome.NoMPpd"
## 
## 
## $`goog:chromeOptions`
## $`goog:chromeOptions`$debuggerAddress
## [1] "localhost:50345"
## 
## 
## $networkConnectionEnabled
## [1] FALSE
## 
## $pageLoadStrategy
## [1] "normal"
## 
## $platformName
## [1] "mac os x"
## 
## $proxy
## named list()
## 
## $setWindowRect
## [1] TRUE
## 
## $strictFileInteractability
## [1] FALSE
## 
## $timeouts
## $timeouts$implicit
## [1] 0
## 
## $timeouts$pageLoad
## [1] 300000
## 
## $timeouts$script
## [1] 30000
## 
## 
## $unhandledPromptBehavior
## [1] "dismiss and notify"
## 
## $`webauthn:virtualAuthenticators`
## [1] TRUE
## 
## $webdriver.remote.sessionid
## [1] "4a9967ab91473c9ed1b01cabbc09dcd2"
## 
## $id
## [1] "4a9967ab91473c9ed1b01cabbc09dcd2"
remote_driver <- driver[["client"]] 
remote_driver$navigate(url)
# retrieve the article

main_article <- remote_driver$findElement(using = "class", value="p402_premium")

text <- main_article$getElementText()

Text is a messy list, you need to do some cleaning again.

# let us clean those special characters like \n \t, etc.

tidy_text <- text[[1]] %>% 
  # remove all whitespaces, note it is regex \t
  str_replace_all("\\s"," ") %>% 
  # reove some weird punct
  str_replace_all('\\"',"") %>% 
  # remove some double spaces
  str_squish %>% 
  # reve spaces at the begining and end of the text
  str_trim %>% 
  # lower case
  tolower()

tidy_text
## [1] "local news fayetteville mayor says protesters must move from market house tags: protest, black lives matter, fayetteville market house posted july 13, 2020 3:37 p.m. edt updated july 13, 2020 6:16 p.m. edt by gilbert baez, wral fayetteville reporter fayetteville, n.c. — after nearly a week camped out at the fayetteville market house to demand more police accountability and more community resources, it's time for protesters to move their sit-in to another location, mayor mitch colvin said monday. the protest by a group called ville's voice started last week, with the group demanding a community center and garden, a citizens review board and an internal affairs department separate from the police department, among other items. colvin said last week that orange street school would be turned into a community center, meeting one of the demands. the city council also plans to discuss creating a review board for the police department, he said. but on monday, the mayor said the occupation of the market house area downtown had gone on long enough and was no longer safe for the demonstrators or members of the public. right now, they're in the middle of a four-way intersection in a traffic circle, which is definitely not safe for them or others who come to support or come to and from it, he said. advertising colvin said he offered the demonstrators several alternative locations where they could continue to exercise their right to protest, but they turned him down. at the end of the day, public safety is our no. 1 priority, he said. the police chief and the city attorney's office basically know what the law is – they've clarified that – and now it's just like any other matter with the police department. police chief gina hawkins couldn't be reached monday for comment on when and how the protesters and their tents would be removed. activist rakeem jones said the campsite is the protesters' way of helping the public and getting better acquainted with police officers stationed nearby. we introduce ourselves to every officer, jones said. just as we feed these homeless people, we feed the officers. we give them water and drinks. we take care of them. we take care of the community. anybody that walks past here, we offer them something. whenever the mayor is talking about issues of public safety, we really want him to recognize the actual issues of public safety, activist mario benaveante said. the issue is about police brutality and all these incidents we can rectify or prevent from happening. the market house has stood since 1832, and some slaves were sold there before the civil war. rioters tried to set it on fire in may, and a black lives matter mural was later painted on the pavement around the building. the fayetteville city council voted last month to remove the historic building from the city seal. get coronavirus updates the latest coronavirus news from wral delivered daily to your inbox. for more news about the coronavirus and resources for tracking the virus and protecting your family, click here. suggest a correction more on this peaceful walk in support of fayetteville police met by protesters protesters camp outside fayetteville market house, make demands of city, police protesters break into, set fire at historic building in fayetteville black lives matter painting encircles fayetteville market house show all recommended sponsored content these are probably the most cryptic tombstones that exist looking at these unexplained epitaphs on tombstones, you can theorize various different fates that happened to those who dictated them. by ranker top articles cooper moves nc into phase 2.5, allowing more businesses to reopen but expanding mask mandate read more read more read more read more read more"

VOILA, we have a nice tidy text!!!

Let us then use coreNLP do some text processing in R (FINALLY :))

here is a document for coreNLP in R https://cran.r-project.org/web/packages/coreNLP/coreNLP.pdf

#install.packages("coreNLP")
# or devtools::install_github("statsmaths/coreNLP")
library(coreNLP)
coreNLP::downloadCoreNLP()
## [1] 0
initCoreNLP()
# Let us annotate our text
output = annotateString(tidy_text)
output
## 
## A CoreNLP Annotation:
##   num. sentences: 26 
##   num. tokens: 687

Once you do annotation, you can have the following information via getToken, getDependency and getSentiment

I am not a computational linguist, so we are not going to discuss details about how to read dependency trees, etc. You can check Google NLP tutorials and other complin for more details.

getToken(output)
##     sentence id          token          lemma CharacterOffsetBegin
## 1          1  1          local          local                    0
## 2          1  2           news           news                    6
## 3          1  3   fayetteville   fayetteville                   11
## 4          1  4          mayor          mayor                   24
## 5          1  5           says            say                   30
## 6          1  6     protesters      protester                   35
## 7          1  7           must           must                   46
## 8          1  8           move           move                   51
## 9          1  9           from           from                   56
## 10         1 10         market         market                   61
## 11         1 11          house          house                   68
## 12         1 12           tags            tag                   74
## 13         1 13              :              :                   78
## 14         1 14        protest        protest                   80
## 15         1 15              ,              ,                   87
## 16         1 16          black          black                   89
## 17         1 17          lives           life                   95
## 18         1 18         matter         matter                  101
## 19         1 19              ,              ,                  107
## 20         1 20   fayetteville   fayetteville                  109
## 21         1 21         market         market                  122
## 22         1 22          house          house                  129
## 23         1 23         posted           post                  135
## 24         1 24           july           july                  142
## 25         1 25             13             13                  147
## 26         1 26              ,              ,                  149
## 27         1 27           2020           2020                  151
## 28         1 28           3:37           3:37                  156
## 29         1 29           p.m.           p.m.                  161
## 30         1 30            edt            edt                  166
## 31         1 31        updated         update                  170
## 32         1 32           july           july                  178
## 33         1 33             13             13                  183
## 34         1 34              ,              ,                  185
## 35         1 35           2020           2020                  187
## 36         1 36           6:16           6:16                  192
## 37         1 37           p.m.           p.m.                  197
## 38         1 38            edt            edt                  202
## 39         1 39             by             by                  206
## 40         1 40        gilbert        gilbert                  209
## 41         1 41           baez           baez                  217
## 42         1 42              ,              ,                  221
## 43         1 43           wral           wral                  223
## 44         1 44   fayetteville   fayetteville                  228
## 45         1 45       reporter       reporter                  241
## 46         1 46   fayetteville   fayetteville                  250
## 47         1 47              ,              ,                  262
## 48         1 48           n.c.           n.c.                  264
## 49         1 49             --             --                  269
## 50         1 50          after          after                  271
## 51         1 51         nearly         nearly                  277
## 52         1 52              a              a                  284
## 53         1 53           week           week                  286
## 54         1 54         camped           camp                  291
## 55         1 55            out            out                  298
## 56         1 56             at             at                  302
## 57         1 57            the            the                  305
## 58         1 58   fayetteville   fayetteville                  309
## 59         1 59         market         market                  322
## 60         1 60          house          house                  329
## 61         1 61             to             to                  335
## 62         1 62         demand         demand                  338
## 63         1 63           more           more                  345
## 64         1 64         police         police                  350
## 65         1 65 accountability accountability                  357
## 66         1 66            and            and                  372
## 67         1 67           more           more                  376
## 68         1 68      community      community                  381
## 69         1 69      resources       resource                  391
## 70         1 70              ,              ,                  400
## 71         1 71             it             it                  402
## 72         1 72             's             be                  404
## 73         1 73           time           time                  407
## 74         1 74            for            for                  412
## 75         1 75     protesters      protester                  416
## 76         1 76             to             to                  427
## 77         1 77           move           move                  430
## 78         1 78          their           they                  435
## 79         1 79         sit-in         sit-in                  441
## 80         1 80             to             to                  448
## 81         1 81        another        another                  451
## 82         1 82       location       location                  459
## 83         1 83              ,              ,                  467
## 84         1 84          mayor          mayor                  469
## 85         1 85          mitch          mitch                  475
## 86         1 86         colvin         colvin                  481
## 87         1 87           said            say                  488
## 88         1 88         monday         monday                  493
## 89         1 89              .              .                  499
## 90         2  1            the            the                  501
## 91         2  2        protest        protest                  505
## 92         2  3             by             by                  513
## 93         2  4              a              a                  516
## 94         2  5          group          group                  518
## 95         2  6         called           call                  524
## 96         2  7          ville          ville                  531
## 97         2  8             's             's                  536
## 98         2  9          voice          voice                  539
## 99         2 10        started          start                  545
## 100        2 11           last           last                  553
## 101        2 12           week           week                  558
## 102        2 13              ,              ,                  562
## 103        2 14           with           with                  564
## 104        2 15            the            the                  569
## 105        2 16          group          group                  573
## 106        2 17      demanding         demand                  579
## 107        2 18              a              a                  589
## 108        2 19      community      community                  591
## 109        2 20         center         center                  601
## 110        2 21            and            and                  608
## 111        2 22         garden         garden                  612
## 112        2 23              ,              ,                  618
## 113        2 24              a              a                  620
## 114        2 25       citizens        citizen                  622
## 115        2 26         review         review                  631
## 116        2 27          board          board                  638
## 117        2 28            and            and                  644
## 118        2 29             an              a                  648
## 119        2 30       internal       internal                  651
## 120        2 31        affairs         affair                  660
## 121        2 32     department     department                  668
## 122        2 33       separate       separate                  679
## 123        2 34           from           from                  688
## 124        2 35            the            the                  693
## 125        2 36         police         police                  697
## 126        2 37     department     department                  704
## 127        2 38              ,              ,                  714
## 128        2 39          among          among                  716
## 129        2 40          other          other                  722
## 130        2 41          items           item                  728
## 131        2 42              .              .                  733
## 132        3  1         colvin         colvin                  735
## 133        3  2           said            say                  742
## 134        3  3           last           last                  747
## 135        3  4           week           week                  752
## 136        3  5           that           that                  757
## 137        3  6         orange         orange                  762
## 138        3  7         street         street                  769
## 139        3  8         school         school                  776
## 140        3  9          would          would                  783
## 141        3 10             be             be                  789
## 142        3 11         turned           turn                  792
## 143        3 12           into           into                  799
## 144        3 13              a              a                  804
## 145        3 14      community      community                  806
## 146        3 15         center         center                  816
## 147        3 16              ,              ,                  822
## 148        3 17        meeting           meet                  824
## 149        3 18            one            one                  832
## 150        3 19             of             of                  836
## 151        3 20            the            the                  839
## 152        3 21        demands         demand                  843
## 153        3 22              .              .                  850
## 154        4  1            the            the                  852
## 155        4  2           city           city                  856
## 156        4  3        council        council                  861
## 157        4  4           also           also                  869
## 158        4  5          plans           plan                  874
## 159        4  6             to             to                  880
## 160        4  7        discuss        discuss                  883
## 161        4  8       creating         create                  891
## 162        4  9              a              a                  900
## 163        4 10         review         review                  902
## 164        4 11          board          board                  909
## 165        4 12            for            for                  915
## 166        4 13            the            the                  919
## 167        4 14         police         police                  923
## 168        4 15     department     department                  930
## 169        4 16              ,              ,                  940
## 170        4 17             he             he                  942
## 171        4 18           said            say                  945
## 172        4 19              .              .                  949
## 173        5  1            but            but                  951
## 174        5  2             on             on                  955
## 175        5  3         monday         monday                  958
## 176        5  4              ,              ,                  964
## 177        5  5            the            the                  966
## 178        5  6          mayor          mayor                  970
## 179        5  7           said            say                  976
## 180        5  8            the            the                  981
## 181        5  9     occupation     occupation                  985
## 182        5 10             of             of                  996
## 183        5 11            the            the                  999
## 184        5 12         market         market                 1003
## 185        5 13          house          house                 1010
## 186        5 14           area           area                 1016
## 187        5 15       downtown       downtown                 1021
## 188        5 16            had           have                 1030
## 189        5 17           gone             go                 1034
## 190        5 18             on             on                 1039
## 191        5 19           long           long                 1042
## 192        5 20         enough         enough                 1047
## 193        5 21            and            and                 1054
## 194        5 22            was             be                 1058
## 195        5 23             no             no                 1062
## 196        5 24         longer         longer                 1065
## 197        5 25           safe           safe                 1072
## 198        5 26            for            for                 1077
## 199        5 27            the            the                 1081
## 200        5 28  demonstrators   demonstrator                 1085
## 201        5 29             or             or                 1099
## 202        5 30        members         member                 1102
## 203        5 31             of             of                 1110
## 204        5 32            the            the                 1113
## 205        5 33         public         public                 1117
## 206        5 34              .              .                 1123
## 207        6  1          right          right                 1125
## 208        6  2            now            now                 1131
## 209        6  3              ,              ,                 1134
## 210        6  4           they           they                 1136
## 211        6  5            're             be                 1140
## 212        6  6             in             in                 1144
## 213        6  7            the            the                 1147
## 214        6  8         middle         middle                 1151
## 215        6  9             of             of                 1158
## 216        6 10              a              a                 1161
## 217        6 11       four-way       four-way                 1163
## 218        6 12   intersection   intersection                 1172
## 219        6 13             in             in                 1185
## 220        6 14              a              a                 1188
## 221        6 15        traffic        traffic                 1190
## 222        6 16         circle         circle                 1198
## 223        6 17              ,              ,                 1204
## 224        6 18          which          which                 1206
## 225        6 19             is             be                 1212
## 226        6 20     definitely     definitely                 1215
## 227        6 21            not            not                 1226
## 228        6 22           safe           safe                 1230
## 229        6 23            for            for                 1235
## 230        6 24           them           they                 1239
## 231        6 25             or             or                 1244
## 232        6 26         others          other                 1247
## 233        6 27            who            who                 1254
## 234        6 28           come           come                 1258
## 235        6 29             to             to                 1263
## 236        6 30        support        support                 1266
## 237        6 31             or             or                 1274
## 238        6 32           come           come                 1277
## 239        6 33             to             to                 1282
## 240        6 34            and            and                 1285
## 241        6 35           from           from                 1289
## 242        6 36             it             it                 1294
## 243        6 37              ,              ,                 1296
## 244        6 38             he             he                 1298
## 245        6 39           said            say                 1301
## 246        6 40              .              .                 1305
## 247        7  1    advertising    advertising                 1307
## 248        7  2         colvin         colvin                 1319
## 249        7  3           said            say                 1326
## 250        7  4             he             he                 1331
## 251        7  5        offered          offer                 1334
## 252        7  6            the            the                 1342
## 253        7  7  demonstrators   demonstrator                 1346
## 254        7  8        several        several                 1360
## 255        7  9    alternative    alternative                 1368
## 256        7 10      locations       location                 1380
## 257        7 11          where          where                 1390
## 258        7 12           they           they                 1396
## 259        7 13          could          could                 1401
## 260        7 14       continue       continue                 1407
## 261        7 15             to             to                 1416
## 262        7 16       exercise       exercise                 1419
## 263        7 17          their           they                 1428
## 264        7 18          right          right                 1434
## 265        7 19             to             to                 1440
## 266        7 20        protest        protest                 1443
## 267        7 21              ,              ,                 1450
## 268        7 22            but            but                 1452
## 269        7 23           they           they                 1456
## 270        7 24         turned           turn                 1461
## 271        7 25            him             he                 1468
## 272        7 26           down           down                 1472
## 273        7 27              .              .                 1476
## 274        8  1             at             at                 1478
## 275        8  2            the            the                 1481
## 276        8  3            end            end                 1485
## 277        8  4             of             of                 1489
## 278        8  5            the            the                 1492
## 279        8  6            day            day                 1496
## 280        8  7              ,              ,                 1499
## 281        8  8         public         public                 1501
## 282        8  9         safety         safety                 1508
## 283        8 10             is             be                 1515
## 284        8 11            our             we                 1518
## 285        8 12            no.            no.                 1522
## 286        8 13              1              1                 1526
## 287        8 14       priority       priority                 1528
## 288        8 15              ,              ,                 1536
## 289        8 16             he             he                 1538
## 290        8 17           said            say                 1541
## 291        8 18              .              .                 1545
## 292        9  1            the            the                 1547
## 293        9  2         police         police                 1551
## 294        9  3          chief          chief                 1558
## 295        9  4            and            and                 1564
## 296        9  5            the            the                 1568
## 297        9  6           city           city                 1572
## 298        9  7       attorney       attorney                 1577
## 299        9  8             's             's                 1585
## 300        9  9         office         office                 1588
## 301        9 10      basically      basically                 1595
## 302        9 11           know           know                 1605
## 303        9 12           what           what                 1610
## 304        9 13            the            the                 1615
## 305        9 14            law            law                 1619
## 306        9 15             is             be                 1623
## 307        9 16             --             --                 1626
## 308        9 17           they           they                 1628
## 309        9 18            've           have                 1632
## 310        9 19      clarified        clarify                 1636
## 311        9 20           that           that                 1646
## 312        9 21             --             --                 1651
## 313        9 22            and            and                 1653
## 314        9 23            now            now                 1657
## 315        9 24             it             it                 1661
## 316        9 25             's             be                 1663
## 317        9 26           just           just                 1666
## 318        9 27           like           like                 1671
## 319        9 28            any            any                 1676
## 320        9 29          other          other                 1680
## 321        9 30         matter         matter                 1686
## 322        9 31           with           with                 1693
## 323        9 32            the            the                 1698
## 324        9 33         police         police                 1702
## 325        9 34     department     department                 1709
## 326        9 35              .              .                 1719
## 327       10  1         police         police                 1721
## 328       10  2          chief          chief                 1728
## 329       10  3           gina           gina                 1734
## 330       10  4        hawkins         hawkin                 1739
## 331       10  5          could          could                 1747
## 332       10  6            n't            not                 1752
## 333       10  7             be             be                 1756
## 334       10  8        reached          reach                 1759
## 335       10  9         monday         monday                 1767
## 336       10 10            for            for                 1774
## 337       10 11        comment        comment                 1778
## 338       10 12             on             on                 1786
## 339       10 13           when           when                 1789
## 340       10 14            and            and                 1794
## 341       10 15            how            how                 1798
## 342       10 16            the            the                 1802
## 343       10 17     protesters      protester                 1806
## 344       10 18            and            and                 1817
## 345       10 19          their           they                 1821
## 346       10 20          tents           tent                 1827
## 347       10 21          would          would                 1833
## 348       10 22             be             be                 1839
## 349       10 23        removed         remove                 1842
## 350       10 24              .              .                 1849
## 351       11  1       activist       activist                 1851
## 352       11  2         rakeem         rakeem                 1860
## 353       11  3          jones           jone                 1867
## 354       11  4           said            say                 1873
## 355       11  5            the            the                 1878
## 356       11  6       campsite       campsite                 1882
## 357       11  7             is             be                 1891
## 358       11  8            the            the                 1894
## 359       11  9     protesters      protester                 1898
## 360       11 10              '              '                 1908
## 361       11 11            way            way                 1910
## 362       11 12             of             of                 1914
## 363       11 13        helping           help                 1917
## 364       11 14            the            the                 1925
## 365       11 15         public         public                 1929
## 366       11 16            and            and                 1936
## 367       11 17        getting            get                 1940
## 368       11 18         better         better                 1948
## 369       11 19     acquainted       acquaint                 1955
## 370       11 20           with           with                 1966
## 371       11 21         police         police                 1971
## 372       11 22       officers        officer                 1978
## 373       11 23      stationed        station                 1987
## 374       11 24         nearby         nearby                 1997
## 375       11 25              .              .                 2003
## 376       12  1             we             we                 2005
## 377       12  2      introduce      introduce                 2008
## 378       12  3      ourselves      ourselves                 2018
## 379       12  4             to             to                 2028
## 380       12  5          every          every                 2031
## 381       12  6        officer        officer                 2037
## 382       12  7              ,              ,                 2044
## 383       12  8          jones           jone                 2046
## 384       12  9           said            say                 2052
## 385       12 10              .              .                 2056
## 386       13  1           just           just                 2058
## 387       13  2             as             as                 2063
## 388       13  3             we             we                 2066
## 389       13  4           feed           feed                 2069
## 390       13  5          these          these                 2074
## 391       13  6       homeless       homeless                 2080
## 392       13  7         people         people                 2089
## 393       13  8              ,              ,                 2095
## 394       13  9             we             we                 2097
## 395       13 10           feed           feed                 2100
## 396       13 11            the            the                 2105
## 397       13 12       officers        officer                 2109
## 398       13 13              .              .                 2117
## 399       14  1             we             we                 2119
## 400       14  2           give           give                 2122
## 401       14  3           them           they                 2127
## 402       14  4          water          water                 2132
## 403       14  5            and            and                 2138
## 404       14  6         drinks          drink                 2142
## 405       14  7              .              .                 2148
## 406       15  1             we             we                 2150
## 407       15  2           take           take                 2153
## 408       15  3           care           care                 2158
## 409       15  4             of             of                 2163
## 410       15  5           them           they                 2166
## 411       15  6              .              .                 2170
## 412       16  1             we             we                 2172
## 413       16  2           take           take                 2175
## 414       16  3           care           care                 2180
## 415       16  4             of             of                 2185
## 416       16  5            the            the                 2188
## 417       16  6      community      community                 2192
## 418       16  7              .              .                 2201
## 419       17  1        anybody        anybody                 2203
## 420       17  2           that           that                 2211
## 421       17  3          walks           walk                 2216
## 422       17  4           past           past                 2222
## 423       17  5           here           here                 2227
## 424       17  6              ,              ,                 2231
## 425       17  7             we             we                 2233
## 426       17  8          offer          offer                 2236
## 427       17  9           them           they                 2242
## 428       17 10      something      something                 2247
## 429       17 11              .              .                 2256
## 430       18  1       whenever       whenever                 2258
## 431       18  2            the            the                 2267
## 432       18  3          mayor          mayor                 2271
## 433       18  4             is             be                 2277
## 434       18  5        talking           talk                 2280
## 435       18  6          about          about                 2288
## 436       18  7         issues          issue                 2294
## 437       18  8             of             of                 2301
## 438       18  9         public         public                 2304
## 439       18 10         safety         safety                 2311
## 440       18 11              ,              ,                 2317
## 441       18 12             we             we                 2319
## 442       18 13         really         really                 2322
## 443       18 14           want           want                 2329
## 444       18 15            him             he                 2334
## 445       18 16             to             to                 2338
## 446       18 17      recognize      recognize                 2341
## 447       18 18            the            the                 2351
## 448       18 19         actual         actual                 2355
## 449       18 20         issues          issue                 2362
## 450       18 21             of             of                 2369
## 451       18 22         public         public                 2372
## 452       18 23         safety         safety                 2379
## 453       18 24              ,              ,                 2385
## 454       18 25       activist       activist                 2387
## 455       18 26          mario          mario                 2396
## 456       18 27     benaveante     benaveante                 2402
## 457       18 28           said            say                 2413
## 458       18 29              .              .                 2417
## 459       19  1            the            the                 2419
## 460       19  2          issue          issue                 2423
## 461       19  3             is             be                 2429
## 462       19  4          about          about                 2432
## 463       19  5         police         police                 2438
## 464       19  6      brutality      brutality                 2445
## 465       19  7            and            and                 2455
## 466       19  8            all            all                 2459
## 467       19  9          these          these                 2463
## 468       19 10      incidents       incident                 2469
## 469       19 11             we             we                 2479
## 470       19 12            can            can                 2482
## 471       19 13        rectify        rectify                 2486
## 472       19 14             or             or                 2494
## 473       19 15        prevent        prevent                 2497
## 474       19 16           from           from                 2505
## 475       19 17      happening         happen                 2510
## 476       19 18              .              .                 2519
## 477       20  1            the            the                 2521
## 478       20  2         market         market                 2525
## 479       20  3          house          house                 2532
## 480       20  4            has           have                 2538
## 481       20  5          stood          stand                 2542
## 482       20  6          since          since                 2548
## 483       20  7           1832           1832                 2554
## 484       20  8              ,              ,                 2558
## 485       20  9            and            and                 2560
## 486       20 10           some           some                 2564
## 487       20 11         slaves          slave                 2569
## 488       20 12           were             be                 2576
## 489       20 13           sold           sell                 2581
## 490       20 14          there          there                 2586
## 491       20 15         before         before                 2592
## 492       20 16            the            the                 2599
## 493       20 17          civil          civil                 2603
## 494       20 18            war            war                 2609
## 495       20 19              .              .                 2612
## 496       21  1        rioters         rioter                 2614
## 497       21  2          tried            try                 2622
## 498       21  3             to             to                 2628
## 499       21  4            set            set                 2631
## 500       21  5             it             it                 2635
## 501       21  6             on             on                 2638
## 502       21  7           fire           fire                 2641
## 503       21  8             in             in                 2646
## 504       21  9            may            may                 2649
## 505       21 10              ,              ,                 2652
## 506       21 11            and            and                 2654
## 507       21 12              a              a                 2658
## 508       21 13          black          black                 2660
## 509       21 14          lives           life                 2666
## 510       21 15         matter         matter                 2672
## 511       21 16          mural          mural                 2679
## 512       21 17            was             be                 2685
## 513       21 18          later          later                 2689
## 514       21 19        painted          paint                 2695
## 515       21 20             on             on                 2703
## 516       21 21            the            the                 2706
## 517       21 22       pavement       pavement                 2710
## 518       21 23         around         around                 2719
## 519       21 24            the            the                 2726
## 520       21 25       building       building                 2730
## 521       21 26              .              .                 2738
## 522       22  1            the            the                 2740
## 523       22  2   fayetteville   fayetteville                 2744
## 524       22  3           city           city                 2757
## 525       22  4        council        council                 2762
## 526       22  5          voted           vote                 2770
## 527       22  6           last           last                 2776
## 528       22  7          month          month                 2781
## 529       22  8             to             to                 2787
## 530       22  9         remove         remove                 2790
## 531       22 10            the            the                 2797
## 532       22 11       historic       historic                 2801
## 533       22 12       building       building                 2810
## 534       22 13           from           from                 2819
## 535       22 14            the            the                 2824
## 536       22 15           city           city                 2828
## 537       22 16           seal           seal                 2833
## 538       22 17              .              .                 2837
## 539       23  1            get            get                 2839
## 540       23  2    coronavirus    coronavirus                 2843
## 541       23  3        updates         update                 2855
## 542       23  4            the            the                 2863
## 543       23  5         latest         latest                 2867
## 544       23  6    coronavirus    coronavirus                 2874
## 545       23  7           news           news                 2886
## 546       23  8           from           from                 2891
## 547       23  9           wral           wral                 2896
## 548       23 10      delivered        deliver                 2901
## 549       23 11          daily          daily                 2911
## 550       23 12             to             to                 2917
## 551       23 13           your            you                 2920
## 552       23 14          inbox          inbox                 2925
## 553       23 15              .              .                 2930
## 554       24  1            for            for                 2932
## 555       24  2           more           more                 2936
## 556       24  3           news           news                 2941
## 557       24  4          about          about                 2946
## 558       24  5            the            the                 2952
## 559       24  6    coronavirus    coronavirus                 2956
## 560       24  7            and            and                 2968
## 561       24  8      resources       resource                 2972
## 562       24  9            for            for                 2982
## 563       24 10       tracking          track                 2986
## 564       24 11            the            the                 2995
## 565       24 12          virus          virus                 2999
## 566       24 13            and            and                 3005
## 567       24 14     protecting        protect                 3009
## 568       24 15           your            you                 3020
## 569       24 16         family         family                 3025
## 570       24 17              ,              ,                 3031
## 571       24 18          click          click                 3033
## 572       24 19           here           here                 3039
## 573       24 20              .              .                 3043
## 574       25  1        suggest        suggest                 3045
## 575       25  2              a              a                 3053
## 576       25  3     correction     correction                 3055
## 577       25  4           more           more                 3066
## 578       25  5             on             on                 3071
## 579       25  6           this           this                 3074
## 580       25  7       peaceful       peaceful                 3079
## 581       25  8           walk           walk                 3088
## 582       25  9             in             in                 3093
## 583       25 10        support        support                 3096
## 584       25 11             of             of                 3104
## 585       25 12   fayetteville   fayetteville                 3107
## 586       25 13         police         police                 3120
## 587       25 14            met           meet                 3127
## 588       25 15             by             by                 3131
## 589       25 16     protesters      protester                 3134
## 590       25 17     protesters      protester                 3145
## 591       25 18           camp           camp                 3156
## 592       25 19        outside        outside                 3161
## 593       25 20   fayetteville   fayetteville                 3169
## 594       25 21         market         market                 3182
## 595       25 22          house          house                 3189
## 596       25 23              ,              ,                 3194
## 597       25 24           make           make                 3196
## 598       25 25        demands         demand                 3201
## 599       25 26             of             of                 3209
## 600       25 27           city           city                 3212
## 601       25 28              ,              ,                 3216
## 602       25 29         police         police                 3218
## 603       25 30     protesters      protester                 3225
## 604       25 31          break          break                 3236
## 605       25 32           into           into                 3242
## 606       25 33              ,              ,                 3246
## 607       25 34            set            set                 3248
## 608       25 35           fire           fire                 3252
## 609       25 36             at             at                 3257
## 610       25 37       historic       historic                 3260
## 611       25 38       building       building                 3269
## 612       25 39             in             in                 3278
## 613       25 40   fayetteville   fayetteville                 3281
## 614       25 41          black          black                 3294
## 615       25 42          lives           life                 3300
## 616       25 43         matter         matter                 3306
## 617       25 44       painting       painting                 3313
## 618       25 45      encircles       encircle                 3322
## 619       25 46   fayetteville   fayetteville                 3332
## 620       25 47         market         market                 3345
## 621       25 48          house          house                 3352
## 622       25 49           show           show                 3358
## 623       25 50            all            all                 3363
## 624       25 51    recommended      recommend                 3367
## 625       25 52      sponsored        sponsor                 3379
## 626       25 53        content        content                 3389
## 627       25 54          these          these                 3397
## 628       25 55            are             be                 3403
## 629       25 56       probably       probably                 3407
## 630       25 57            the            the                 3416
## 631       25 58           most           most                 3420
## 632       25 59        cryptic        cryptic                 3425
## 633       25 60     tombstones      tombstone                 3433
## 634       25 61           that           that                 3444
## 635       25 62          exist          exist                 3449
## 636       25 63        looking           look                 3455
## 637       25 64             at             at                 3463
## 638       25 65          these          these                 3466
## 639       25 66    unexplained    unexplained                 3472
## 640       25 67       epitaphs        epitaph                 3484
## 641       25 68             on             on                 3493
## 642       25 69     tombstones      tombstone                 3496
## 643       25 70              ,              ,                 3506
## 644       25 71            you            you                 3508
## 645       25 72            can            can                 3512
## 646       25 73       theorize       theorize                 3516
## 647       25 74        various        various                 3525
## 648       25 75      different      different                 3533
## 649       25 76          fates           fate                 3543
## 650       25 77           that           that                 3549
## 651       25 78       happened         happen                 3554
## 652       25 79             to             to                 3563
## 653       25 80          those          those                 3566
## 654       25 81            who            who                 3572
## 655       25 82       dictated        dictate                 3576
## 656       25 83           them           they                 3585
## 657       25 84              .              .                 3589
## 658       26  1             by             by                 3591
## 659       26  2         ranker         ranker                 3594
## 660       26  3            top            top                 3601
## 661       26  4       articles        article                 3605
## 662       26  5         cooper         cooper                 3614
## 663       26  6          moves           move                 3621
## 664       26  7             nc             nc                 3627
## 665       26  8           into           into                 3630
## 666       26  9          phase          phase                 3635
## 667       26 10            2.5            2.5                 3641
## 668       26 11              ,              ,                 3644
## 669       26 12       allowing          allow                 3646
## 670       26 13           more           more                 3655
## 671       26 14     businesses       business                 3660
## 672       26 15             to             to                 3671
## 673       26 16         reopen         reopen                 3674
## 674       26 17            but            but                 3681
## 675       26 18      expanding         expand                 3685
## 676       26 19           mask           mask                 3695
## 677       26 20        mandate        mandate                 3700
## 678       26 21           read           read                 3708
## 679       26 22           more           more                 3713
## 680       26 23           read           read                 3718
## 681       26 24           more           more                 3723
## 682       26 25           read           read                 3728
## 683       26 26           more           more                 3733
## 684       26 27           read           read                 3738
## 685       26 28           more           more                 3743
## 686       26 29           read           read                 3748
## 687       26 30           more           more                 3753
##     CharacterOffsetEnd  POS      NER Speaker
## 1                    5   JJ        O    PER0
## 2                   10   NN        O    PER0
## 3                   23   NN        O    PER0
## 4                   29   NN        O    PER0
## 5                   34  VBZ        O    PER0
## 6                   45  NNS        O    PER0
## 7                   50   MD        O    PER0
## 8                   55   VB        O    PER0
## 9                   60   IN        O    PER0
## 10                  67   NN        O    PER0
## 11                  73   NN        O    PER0
## 12                  78  NNS        O    PER0
## 13                  79    :        O    PER0
## 14                  87   NN        O    PER0
## 15                  88    ,        O    PER0
## 16                  94   JJ        O    PER0
## 17                 100  NNS        O    PER0
## 18                 107   NN        O    PER0
## 19                 108    ,        O    PER0
## 20                 121   NN        O    PER0
## 21                 128   NN        O    PER0
## 22                 134   NN        O    PER0
## 23                 141  VBD        O    PER0
## 24                 146  NNP     DATE    PER0
## 25                 149   CD     DATE    PER0
## 26                 150    ,     DATE    PER0
## 27                 155   CD     DATE    PER0
## 28                 160   CD     TIME    PER0
## 29                 165   NN     TIME    PER0
## 30                 169   NN     TIME    PER0
## 31                 177  VBN        O    PER0
## 32                 182  NNP     DATE    PER0
## 33                 185   CD     DATE    PER0
## 34                 186    ,     DATE    PER0
## 35                 191   CD     DATE    PER0
## 36                 196   CD     TIME    PER0
## 37                 201   NN     TIME    PER0
## 38                 205   NN     TIME    PER0
## 39                 208   IN        O    PER0
## 40                 216   NN        O    PER0
## 41                 221   NN        O    PER0
## 42                 222    ,        O    PER0
## 43                 227   JJ        O    PER0
## 44                 240   NN        O    PER0
## 45                 249   NN        O    PER0
## 46                 262   NN        O    PER0
## 47                 263    ,        O    PER0
## 48                 268   NN        O    PER0
## 49                 270    :        O    PER0
## 50                 276   IN        O    PER0
## 51                 283   RB DURATION    PER0
## 52                 285   DT DURATION    PER0
## 53                 290   NN DURATION    PER0
## 54                 297  VBN        O    PER0
## 55                 301   RP        O    PER0
## 56                 304   IN        O    PER0
## 57                 308   DT        O    PER0
## 58                 321   NN        O    PER0
## 59                 328   NN        O    PER0
## 60                 334   NN        O    PER0
## 61                 337   TO        O    PER0
## 62                 344   VB        O    PER0
## 63                 349  JJR        O    PER0
## 64                 356   NN        O    PER0
## 65                 371   NN        O    PER0
## 66                 375   CC        O    PER0
## 67                 380  JJR        O    PER0
## 68                 390   NN        O    PER0
## 69                 400  NNS        O    PER0
## 70                 401    ,        O    PER0
## 71                 404  PRP        O    PER0
## 72                 406  VBZ        O    PER0
## 73                 411   NN        O    PER0
## 74                 415   IN        O    PER0
## 75                 426  NNS        O    PER0
## 76                 429   TO        O    PER0
## 77                 434   VB        O    PER0
## 78                 440 PRP$        O    PER0
## 79                 447   NN        O    PER0
## 80                 450   TO        O    PER0
## 81                 458   DT        O    PER0
## 82                 467   NN        O    PER0
## 83                 468    ,        O    PER0
## 84                 474   NN        O    PER0
## 85                 480   NN   PERSON    PER0
## 86                 487   NN   PERSON    PER0
## 87                 492  VBD        O    PER0
## 88                 499  NNP     DATE    PER0
## 89                 500    .        O    PER0
## 90                 504   DT        O    PER0
## 91                 512   NN        O    PER0
## 92                 515   IN        O    PER0
## 93                 517   DT        O    PER0
## 94                 523   NN        O    PER0
## 95                 530  VBD        O    PER0
## 96                 536  NNP        O    PER0
## 97                 538  POS        O    PER0
## 98                 544   NN        O    PER0
## 99                 552  VBD        O    PER0
## 100                557   JJ     DATE    PER0
## 101                562   NN     DATE    PER0
## 102                563    ,        O    PER0
## 103                568   IN        O    PER0
## 104                572   DT        O    PER0
## 105                578   NN        O    PER0
## 106                588  VBG        O    PER0
## 107                590   DT        O    PER0
## 108                600   NN        O    PER0
## 109                607   NN        O    PER0
## 110                611   CC        O    PER0
## 111                618   NN        O    PER0
## 112                619    ,        O    PER0
## 113                621   DT        O    PER0
## 114                630  NNS        O    PER0
## 115                637  VBP        O    PER0
## 116                643   NN        O    PER0
## 117                647   CC        O    PER0
## 118                650   DT        O    PER0
## 119                659   JJ        O    PER0
## 120                667  NNS        O    PER0
## 121                678   NN        O    PER0
## 122                687   JJ        O    PER0
## 123                692   IN        O    PER0
## 124                696   DT        O    PER0
## 125                703   NN        O    PER0
## 126                714   NN        O    PER0
## 127                715    ,        O    PER0
## 128                721   IN        O    PER0
## 129                727   JJ        O    PER0
## 130                733  NNS        O    PER0
## 131                734    .        O    PER0
## 132                741   NN   PERSON    PER0
## 133                746  VBD        O    PER0
## 134                751   JJ     DATE    PER0
## 135                756   NN     DATE    PER0
## 136                761  WDT        O    PER0
## 137                768   JJ        O    PER0
## 138                775   NN        O    PER0
## 139                782   NN        O    PER0
## 140                788   MD        O    PER0
## 141                791   VB        O    PER0
## 142                798  VBN        O    PER0
## 143                803   IN        O    PER0
## 144                805   DT        O    PER0
## 145                815   NN        O    PER0
## 146                822   NN        O    PER0
## 147                823    ,        O    PER0
## 148                831  VBG        O    PER0
## 149                835   CD   NUMBER    PER0
## 150                838   IN        O    PER0
## 151                842   DT        O    PER0
## 152                850  NNS        O    PER0
## 153                851    .        O    PER0
## 154                855   DT        O    PER0
## 155                860   NN        O    PER0
## 156                868   NN        O    PER0
## 157                873   RB        O    PER0
## 158                879  VBZ        O    PER0
## 159                882   TO        O    PER0
## 160                890   VB        O    PER0
## 161                899  VBG        O    PER0
## 162                901   DT        O    PER0
## 163                908   NN        O    PER0
## 164                914   NN        O    PER0
## 165                918   IN        O    PER0
## 166                922   DT        O    PER0
## 167                929   NN        O    PER0
## 168                940   NN        O    PER0
## 169                941    ,        O    PER0
## 170                944  PRP        O    PER0
## 171                949  VBD        O    PER0
## 172                950    .        O    PER0
## 173                954   CC        O    PER0
## 174                957   IN        O    PER0
## 175                964  NNP     DATE    PER0
## 176                965    ,        O    PER0
## 177                969   DT        O    PER0
## 178                975   NN        O    PER0
## 179                980  VBD        O    PER0
## 180                984   DT        O    PER0
## 181                995   NN        O    PER0
## 182                998   IN        O    PER0
## 183               1002   DT        O    PER0
## 184               1009   NN        O    PER0
## 185               1015   NN        O    PER0
## 186               1020   NN        O    PER0
## 187               1029   NN        O    PER0
## 188               1033  VBD        O    PER0
## 189               1038  VBN        O    PER0
## 190               1041   RB        O    PER0
## 191               1046   RB        O    PER0
## 192               1053   RB        O    PER0
## 193               1057   CC        O    PER0
## 194               1061  VBD        O    PER0
## 195               1064   RB        O    PER0
## 196               1071   RB        O    PER0
## 197               1076   JJ        O    PER0
## 198               1080   IN        O    PER0
## 199               1084   DT        O    PER0
## 200               1098  NNS        O    PER0
## 201               1101   CC        O    PER0
## 202               1109  NNS        O    PER0
## 203               1112   IN        O    PER0
## 204               1116   DT        O    PER0
## 205               1123   NN        O    PER0
## 206               1124    .        O    PER0
## 207               1130   RB     DATE    PER0
## 208               1134   RB     DATE    PER0
## 209               1135    ,        O    PER0
## 210               1140  PRP        O    PER0
## 211               1143  VBP        O    PER0
## 212               1146   IN        O    PER0
## 213               1150   DT        O    PER0
## 214               1157   NN        O    PER0
## 215               1160   IN        O    PER0
## 216               1162   DT        O    PER0
## 217               1171   JJ        O    PER0
## 218               1184   NN        O    PER0
## 219               1187   IN        O    PER0
## 220               1189   DT        O    PER0
## 221               1197   NN        O    PER0
## 222               1204   NN        O    PER0
## 223               1205    ,        O    PER0
## 224               1211  WDT        O    PER0
## 225               1214  VBZ        O    PER0
## 226               1225   RB        O    PER0
## 227               1229   RB        O    PER0
## 228               1234   JJ        O    PER0
## 229               1238   IN        O    PER0
## 230               1243  PRP        O    PER0
## 231               1246   CC        O    PER0
## 232               1253  NNS        O    PER0
## 233               1257   WP        O    PER0
## 234               1262  VBP        O    PER0
## 235               1265   TO        O    PER0
## 236               1273   VB        O    PER0
## 237               1276   CC        O    PER0
## 238               1281   VB        O    PER0
## 239               1284   TO        O    PER0
## 240               1288   CC        O    PER0
## 241               1293   IN        O    PER0
## 242               1296  PRP        O    PER0
## 243               1297    ,        O    PER0
## 244               1300  PRP        O    PER0
## 245               1305  VBD        O    PER0
## 246               1306    .        O    PER0
## 247               1318   NN        O    PER0
## 248               1325   NN        O    PER0
## 249               1330  VBD        O    PER0
## 250               1333  PRP        O    PER0
## 251               1341  VBD        O    PER0
## 252               1345   DT        O    PER0
## 253               1359  NNS        O    PER0
## 254               1367   JJ        O    PER0
## 255               1379   JJ        O    PER0
## 256               1389  NNS        O    PER0
## 257               1395  WRB        O    PER0
## 258               1400  PRP        O    PER0
## 259               1406   MD        O    PER0
## 260               1415   VB        O    PER0
## 261               1418   TO        O    PER0
## 262               1427   VB        O    PER0
## 263               1433 PRP$        O    PER0
## 264               1439   NN        O    PER0
## 265               1442   TO        O    PER0
## 266               1450   NN        O    PER0
## 267               1451    ,        O    PER0
## 268               1455   CC        O    PER0
## 269               1460  PRP        O    PER0
## 270               1467  VBD        O    PER0
## 271               1471  PRP        O    PER0
## 272               1476   RP        O    PER0
## 273               1477    .        O    PER0
## 274               1480   IN        O    PER0
## 275               1484   DT     DATE    PER0
## 276               1488   NN     DATE    PER0
## 277               1491   IN     DATE    PER0
## 278               1495   DT     DATE    PER0
## 279               1499   NN     DATE    PER0
## 280               1500    ,        O    PER0
## 281               1507   JJ        O    PER0
## 282               1514   NN        O    PER0
## 283               1517  VBZ        O    PER0
## 284               1521 PRP$        O    PER0
## 285               1525   NN        O    PER0
## 286               1527   CD   NUMBER    PER0
## 287               1536   NN        O    PER0
## 288               1537    ,        O    PER0
## 289               1540  PRP        O    PER0
## 290               1545  VBD        O    PER0
## 291               1546    .        O    PER0
## 292               1550   DT        O    PER0
## 293               1557   NN        O    PER0
## 294               1563   NN        O    PER0
## 295               1567   CC        O    PER0
## 296               1571   DT        O    PER0
## 297               1576   NN        O    PER0
## 298               1585   NN        O    PER0
## 299               1587  POS        O    PER0
## 300               1594   NN        O    PER0
## 301               1604   RB        O    PER0
## 302               1609  VBP        O    PER0
## 303               1614   WP        O    PER0
## 304               1618   DT        O    PER0
## 305               1622   NN        O    PER0
## 306               1625  VBZ        O    PER0
## 307               1627    :        O    PER0
## 308               1632  PRP        O    PER0
## 309               1635  VBP        O    PER0
## 310               1645  VBN        O    PER0
## 311               1650   DT        O    PER0
## 312               1652    :        O    PER0
## 313               1656   CC        O    PER0
## 314               1660   RB     DATE    PER0
## 315               1663  PRP        O    PER0
## 316               1665  VBZ        O    PER0
## 317               1670   RB        O    PER0
## 318               1675   IN        O    PER0
## 319               1679   DT        O    PER0
## 320               1685   JJ        O    PER0
## 321               1692   NN        O    PER0
## 322               1697   IN        O    PER0
## 323               1701   DT        O    PER0
## 324               1708   NN        O    PER0
## 325               1719   NN        O    PER0
## 326               1720    .        O    PER0
## 327               1727  NNS        O    PER0
## 328               1733   JJ        O    PER0
## 329               1738   NN        O    PER0
## 330               1746  NNS        O    PER0
## 331               1752   MD        O    PER0
## 332               1755   RB        O    PER0
## 333               1758   VB        O    PER0
## 334               1766  VBN        O    PER0
## 335               1773  NNP     DATE    PER0
## 336               1777   IN        O    PER0
## 337               1785   NN        O    PER0
## 338               1788   IN        O    PER0
## 339               1793  WRB        O    PER0
## 340               1797   CC        O    PER0
## 341               1801  WRB        O    PER0
## 342               1805   DT        O    PER0
## 343               1816  NNS        O    PER0
## 344               1820   CC        O    PER0
## 345               1826 PRP$        O    PER0
## 346               1832  NNS        O    PER0
## 347               1838   MD        O    PER0
## 348               1841   VB        O    PER0
## 349               1849  VBN        O    PER0
## 350               1850    .        O    PER0
## 351               1859   NN        O    PER0
## 352               1866   NN        O    PER0
## 353               1872  NNS        O    PER0
## 354               1877  VBD        O    PER0
## 355               1881   DT        O    PER0
## 356               1890   NN        O    PER0
## 357               1893  VBZ        O    PER0
## 358               1897   DT        O    PER0
## 359               1908  NNS        O    PER0
## 360               1909  POS        O    PER0
## 361               1913   NN        O    PER0
## 362               1916   IN        O    PER0
## 363               1924  VBG        O    PER0
## 364               1928   DT        O    PER0
## 365               1935   JJ        O    PER0
## 366               1939   CC        O    PER0
## 367               1947  VBG        O    PER0
## 368               1954  JJR        O    PER0
## 369               1965  VBN        O    PER0
## 370               1970   IN        O    PER0
## 371               1977   NN        O    PER0
## 372               1986  NNS        O    PER0
## 373               1996  VBD        O    PER0
## 374               2003   RB        O    PER0
## 375               2004    .        O    PER0
## 376               2007  PRP        O    PER0
## 377               2017  VBP        O    PER0
## 378               2027  PRP        O    PER0
## 379               2030   TO        O    PER0
## 380               2036   DT        O    PER0
## 381               2044   NN        O    PER0
## 382               2045    ,        O    PER0
## 383               2051  NNS        O    PER0
## 384               2056  VBD        O    PER0
## 385               2057    .        O    PER0
## 386               2062   RB        O    PER0
## 387               2065   IN        O    PER0
## 388               2068  PRP        O    PER0
## 389               2073  VBP        O    PER0
## 390               2079   DT        O    PER0
## 391               2088   JJ        O    PER0
## 392               2095  NNS        O    PER0
## 393               2096    ,        O    PER0
## 394               2099  PRP        O    PER0
## 395               2104  VBP        O    PER0
## 396               2108   DT        O    PER0
## 397               2117  NNS        O    PER0
## 398               2118    .        O    PER0
## 399               2121  PRP        O    PER0
## 400               2126  VBP        O    PER0
## 401               2131  PRP        O    PER0
## 402               2137   NN        O    PER0
## 403               2141   CC        O    PER0
## 404               2148  NNS        O    PER0
## 405               2149    .        O    PER0
## 406               2152  PRP        O    PER0
## 407               2157  VBP        O    PER0
## 408               2162   NN        O    PER0
## 409               2165   IN        O    PER0
## 410               2170  PRP        O    PER0
## 411               2171    .        O    PER0
## 412               2174  PRP        O    PER0
## 413               2179  VBP        O    PER0
## 414               2184   NN        O    PER0
## 415               2187   IN        O    PER0
## 416               2191   DT        O    PER0
## 417               2201   NN        O    PER0
## 418               2202    .        O    PER0
## 419               2210   NN        O    PER0
## 420               2215  WDT        O    PER0
## 421               2221  VBZ        O    PER0
## 422               2226   NN     DATE    PER0
## 423               2231   RB        O    PER0
## 424               2232    ,        O    PER0
## 425               2235  PRP        O    PER0
## 426               2241  VBP        O    PER0
## 427               2246  PRP        O    PER0
## 428               2256   NN        O    PER0
## 429               2257    .        O    PER0
## 430               2266  WRB        O    PER0
## 431               2270   DT        O    PER0
## 432               2276   NN        O    PER0
## 433               2279  VBZ        O    PER0
## 434               2287  VBG        O    PER0
## 435               2293   IN        O    PER0
## 436               2300  NNS        O    PER0
## 437               2303   IN        O    PER0
## 438               2310   JJ        O    PER0
## 439               2317   NN        O    PER0
## 440               2318    ,        O    PER0
## 441               2321  PRP        O    PER0
## 442               2328   RB        O    PER0
## 443               2333  VBP        O    PER0
## 444               2337  PRP        O    PER0
## 445               2340   TO        O    PER0
## 446               2350   VB        O    PER0
## 447               2354   DT        O    PER0
## 448               2361   JJ        O    PER0
## 449               2368  NNS        O    PER0
## 450               2371   IN        O    PER0
## 451               2378   JJ        O    PER0
## 452               2385   NN        O    PER0
## 453               2386    ,        O    PER0
## 454               2395   NN        O    PER0
## 455               2401   NN   PERSON    PER0
## 456               2412   NN   PERSON    PER0
## 457               2417  VBD        O    PER0
## 458               2418    .        O    PER0
## 459               2422   DT        O    PER0
## 460               2428   NN        O    PER0
## 461               2431  VBZ        O    PER0
## 462               2437   IN        O    PER0
## 463               2444   NN        O    PER0
## 464               2454   NN        O    PER0
## 465               2458   CC        O    PER0
## 466               2462  PDT        O    PER0
## 467               2468   DT        O    PER0
## 468               2478  NNS        O    PER0
## 469               2481  PRP        O    PER0
## 470               2485   MD        O    PER0
## 471               2493   VB        O    PER0
## 472               2496   CC        O    PER0
## 473               2504   VB        O    PER0
## 474               2509   IN        O    PER0
## 475               2519  VBG        O    PER0
## 476               2520    .        O    PER0
## 477               2524   DT        O    PER0
## 478               2531   NN        O    PER0
## 479               2537   NN        O    PER0
## 480               2541  VBZ        O    PER0
## 481               2547  VBN        O    PER0
## 482               2553   IN        O    PER0
## 483               2558   CD     DATE    PER0
## 484               2559    ,        O    PER0
## 485               2563   CC        O    PER0
## 486               2568   DT        O    PER0
## 487               2575  NNS        O    PER0
## 488               2580  VBD        O    PER0
## 489               2585  VBN        O    PER0
## 490               2591   RB        O    PER0
## 491               2598   IN        O    PER0
## 492               2602   DT        O    PER0
## 493               2608   JJ        O    PER0
## 494               2612   NN        O    PER0
## 495               2613    .        O    PER0
## 496               2621  NNS        O    PER0
## 497               2627  VBD        O    PER0
## 498               2630   TO        O    PER0
## 499               2634   VB        O    PER0
## 500               2637  PRP        O    PER0
## 501               2640   IN        O    PER0
## 502               2645   NN        O    PER0
## 503               2648   IN        O    PER0
## 504               2652   MD        O    PER0
## 505               2653    ,        O    PER0
## 506               2657   CC        O    PER0
## 507               2659   DT        O    PER0
## 508               2665   JJ        O    PER0
## 509               2671  NNS        O    PER0
## 510               2678  VBP        O    PER0
## 511               2684   NN        O    PER0
## 512               2688  VBD        O    PER0
## 513               2694   RB        O    PER0
## 514               2702  VBN        O    PER0
## 515               2705   IN        O    PER0
## 516               2709   DT        O    PER0
## 517               2718   NN        O    PER0
## 518               2725   IN        O    PER0
## 519               2729   DT        O    PER0
## 520               2738   NN        O    PER0
## 521               2739    .        O    PER0
## 522               2743   DT        O    PER0
## 523               2756   JJ        O    PER0
## 524               2761   NN        O    PER0
## 525               2769   NN        O    PER0
## 526               2775  VBD        O    PER0
## 527               2780   JJ     DATE    PER0
## 528               2786   NN     DATE    PER0
## 529               2789   TO        O    PER0
## 530               2796   VB        O    PER0
## 531               2800   DT        O    PER0
## 532               2809   JJ        O    PER0
## 533               2818   NN        O    PER0
## 534               2823   IN        O    PER0
## 535               2827   DT        O    PER0
## 536               2832   NN        O    PER0
## 537               2837   NN        O    PER0
## 538               2838    .        O    PER0
## 539               2842   VB        O    PER0
## 540               2854   NN        O    PER0
## 541               2862  NNS        O    PER0
## 542               2866   DT        O    PER0
## 543               2873  JJS        O    PER0
## 544               2885   NN        O    PER0
## 545               2890   NN        O    PER0
## 546               2895   IN        O    PER0
## 547               2900   JJ        O    PER0
## 548               2910  VBN        O    PER0
## 549               2916   RB      SET    PER0
## 550               2919   TO        O    PER0
## 551               2924 PRP$        O    PER0
## 552               2930   NN        O    PER0
## 553               2931    .        O    PER0
## 554               2935   IN        O    PER0
## 555               2940  JJR        O    PER0
## 556               2945   NN        O    PER0
## 557               2951   IN        O    PER0
## 558               2955   DT        O    PER0
## 559               2967   NN        O    PER0
## 560               2971   CC        O    PER0
## 561               2981  NNS        O    PER0
## 562               2985   IN        O    PER0
## 563               2994  VBG        O    PER0
## 564               2998   DT        O    PER0
## 565               3004   NN        O    PER0
## 566               3008   CC        O    PER0
## 567               3019  VBG        O    PER0
## 568               3024 PRP$        O    PER0
## 569               3031   NN        O    PER0
## 570               3032    ,        O    PER0
## 571               3038  VBP        O    PER0
## 572               3043   RB        O    PER0
## 573               3044    .        O    PER0
## 574               3052   VB        O    PER0
## 575               3054   DT        O    PER0
## 576               3065   NN        O    PER0
## 577               3070  RBR        O    PER0
## 578               3073   IN        O    PER0
## 579               3078   DT        O    PER0
## 580               3087   JJ        O    PER0
## 581               3092   NN        O    PER0
## 582               3095   IN        O    PER0
## 583               3103   NN        O    PER0
## 584               3106   IN        O    PER0
## 585               3119   NN        O    PER0
## 586               3126   NN        O    PER0
## 587               3130  VBD        O    PER0
## 588               3133   IN        O    PER0
## 589               3144  NNS        O    PER0
## 590               3155  NNS        O    PER0
## 591               3160   NN        O    PER0
## 592               3168   IN        O    PER0
## 593               3181   NN        O    PER0
## 594               3188   NN        O    PER0
## 595               3194   NN        O    PER0
## 596               3195    ,        O    PER0
## 597               3200  VBP        O    PER0
## 598               3208  NNS        O    PER0
## 599               3211   IN        O    PER0
## 600               3216   NN        O    PER0
## 601               3217    ,        O    PER0
## 602               3224   NN        O    PER0
## 603               3235  NNS        O    PER0
## 604               3241  VBP        O    PER0
## 605               3246   IN        O    PER0
## 606               3247    ,        O    PER0
## 607               3251  VBN        O    PER0
## 608               3256   NN        O    PER0
## 609               3259   IN        O    PER0
## 610               3268   JJ        O    PER0
## 611               3277   NN        O    PER0
## 612               3280   IN        O    PER0
## 613               3293   NN        O    PER0
## 614               3299   JJ        O    PER0
## 615               3305  NNS        O    PER0
## 616               3312  VBP        O    PER0
## 617               3321   NN        O    PER0
## 618               3331  VBZ        O    PER0
## 619               3344   NN        O    PER0
## 620               3351   NN        O    PER0
## 621               3357   NN        O    PER0
## 622               3362  VBP        O    PER0
## 623               3366   DT        O    PER0
## 624               3378  VBN        O    PER0
## 625               3388  VBN        O    PER0
## 626               3396   JJ        O    PER0
## 627               3402   DT        O    PER0
## 628               3406  VBP        O    PER0
## 629               3415   RB        O    PER0
## 630               3419   DT        O    PER0
## 631               3424  RBS        O    PER0
## 632               3432   JJ        O    PER0
## 633               3443  NNS        O    PER0
## 634               3448  WDT        O    PER0
## 635               3454  VBP        O    PER0
## 636               3462  VBG        O    PER0
## 637               3465   IN        O    PER0
## 638               3471   DT        O    PER0
## 639               3483   JJ        O    PER0
## 640               3492  NNS        O    PER0
## 641               3495   IN        O    PER0
## 642               3506  NNS        O    PER0
## 643               3507    ,        O    PER0
## 644               3511  PRP        O    PER0
## 645               3515   MD        O    PER0
## 646               3524   VB        O    PER0
## 647               3532   JJ        O    PER0
## 648               3542   JJ        O    PER0
## 649               3548  NNS        O    PER0
## 650               3553  WDT        O    PER0
## 651               3562  VBD        O    PER0
## 652               3565   TO        O    PER0
## 653               3571   DT        O    PER0
## 654               3575   WP        O    PER0
## 655               3584  VBD        O    PER0
## 656               3589  PRP        O    PER0
## 657               3590    .        O    PER0
## 658               3593   IN        O    PER0
## 659               3600   NN        O    PER0
## 660               3604   JJ        O    PER0
## 661               3613  NNS        O    PER0
## 662               3620   NN        O    PER0
## 663               3626  VBZ        O    PER0
## 664               3629   NN        O    PER0
## 665               3634   IN        O    PER0
## 666               3640   NN        O    PER0
## 667               3644   CD   NUMBER    PER0
## 668               3645    ,        O    PER0
## 669               3654  VBG        O    PER0
## 670               3659  JJR        O    PER0
## 671               3670  NNS        O    PER0
## 672               3673   TO        O    PER0
## 673               3680   VB        O    PER0
## 674               3684   CC        O    PER0
## 675               3694  VBG        O    PER0
## 676               3699   NN        O    PER0
## 677               3707   NN        O    PER0
## 678               3712  VBD        O    PER0
## 679               3717  RBR        O    PER0
## 680               3722   VB        O    PER0
## 681               3727  RBR        O    PER0
## 682               3732   VB        O    PER0
## 683               3737  RBR        O    PER0
## 684               3742   VB        O    PER0
## 685               3747  RBR        O    PER0
## 686               3752   VB        O    PER0
## 687               3757  JJR        O    PER0
getDependency(output)
##     sentence       governor      dependent         type governorIdx
## 1          1           ROOT           says         root           0
## 2          1          mayor          local         amod           4
## 3          1          mayor           news     compound           4
## 4          1          mayor   fayetteville     compound           4
## 5          1           says          mayor        nsubj           5
## 6          1           move     protesters        nsubj           8
## 7          1           move           must          aux           8
## 8          1           says           move        ccomp           5
## 9          1           tags           from         case          12
## 10         1           tags         market     compound          12
## 11         1           tags          house     compound          12
## 12         1           move           tags    nmod:from           8
## 13         1           says              :        punct           5
## 14         1         posted        protest        nsubj          23
## 15         1        protest              ,        punct          14
## 16         1         matter          black         amod          18
## 17         1         matter          lives     compound          18
## 18         1        protest         matter        appos          14
## 19         1         matter              ,        punct          18
## 20         1          house   fayetteville     compound          22
## 21         1          house         market     compound          22
## 22         1         matter          house        appos          18
## 23         1           says         posted    parataxis           5
## 24         1         posted           july         dobj          23
## 25         1           july             13       nummod          24
## 26         1           july              ,        punct          24
## 27         1           july           2020       nummod          24
## 28         1           p.m.           3:37       nummod          29
## 29         1         posted           p.m.    nmod:tmod          23
## 30         1         posted            edt        xcomp          23
## 31         1            edt        updated         amod          30
## 32         1         posted           july    nmod:tmod          23
## 33         1           july             13       nummod          32
## 34         1           july              ,        punct          32
## 35         1           july           2020       nummod          32
## 36         1            edt           6:16       nummod          38
## 37         1            edt           p.m.     compound          38
## 38         1         posted            edt         dobj          23
## 39         1           baez             by         case          41
## 40         1           baez        gilbert     compound          41
## 41         1         posted           baez      nmod:by          23
## 42         1           baez              ,        punct          41
## 43         1   fayetteville           wral         amod          46
## 44         1   fayetteville   fayetteville     compound          46
## 45         1   fayetteville       reporter     compound          46
## 46         1           baez   fayetteville        appos          41
## 47         1   fayetteville              ,        punct          46
## 48         1   fayetteville           n.c.        appos          46
## 49         1           says             --        punct           5
## 50         1         camped          after         mark          54
## 51         1           week         nearly       advmod          53
## 52         1           week              a          det          53
## 53         1         camped           week          dep          54
## 54         1           time         camped        advcl          73
## 55         1         camped            out compound:prt          54
## 56         1          house             at         case          60
## 57         1          house            the          det          60
## 58         1          house   fayetteville     compound          60
## 59         1          house         market     compound          60
## 60         1         camped          house      nmod:at          54
## 61         1         demand             to         mark          62
## 62         1         camped         demand        xcomp          54
## 63         1 accountability           more         amod          65
## 64         1 accountability         police     compound          65
## 65         1         demand accountability         dobj          62
## 66         1 accountability            and           cc          65
## 67         1      resources           more         amod          69
## 68         1      resources      community     compound          69
## 69         1         demand      resources         dobj          62
## 70         1 accountability      resources     conj:and          65
## 71         1           time              ,        punct          73
## 72         1           time             it        nsubj          73
## 73         1           time             's          cop          73
## 74         1           says           time    parataxis           5
## 75         1     protesters            for         case          75
## 76         1           time     protesters     nmod:for          73
## 77         1           move             to         mark          77
## 78         1     protesters           move          acl          75
## 79         1         sit-in          their    nmod:poss          79
## 80         1           move         sit-in         dobj          77
## 81         1       location             to         case          82
## 82         1       location        another          det          82
## 83         1           move       location      nmod:to          77
## 84         1           says              ,        punct           5
## 85         1         colvin          mayor     compound          86
## 86         1         colvin          mitch     compound          86
## 87         1           said         colvin        nsubj          87
## 88         1           says           said    parataxis           5
## 89         1           said         monday    nmod:tmod          87
## 90         1           says              .        punct           5
## 91         2           ROOT         review         root           0
## 92         2        protest            the          det           2
## 93         2         called        protest        nsubj           6
## 94         2          group             by         case           5
## 95         2          group              a          det           5
## 96         2        protest          group      nmod:by           2
## 97         2         review         called        ccomp          26
## 98         2          voice          ville    nmod:poss           9
## 99         2          ville             's         case           7
## 100        2        started          voice        nsubj          10
## 101        2         called        started        ccomp           6
## 102        2           week           last         amod          12
## 103        2        started           week    nmod:tmod          10
## 104        2        started              ,        punct          10
## 105        2          group           with         case          16
## 106        2          group            the          det          16
## 107        2        started          group    nmod:with          10
## 108        2          group      demanding          acl          16
## 109        2         center              a          det          20
## 110        2         center      community     compound          20
## 111        2      demanding         center         dobj          17
## 112        2         center            and           cc          20
## 113        2      demanding         garden         dobj          17
## 114        2         center         garden     conj:and          20
## 115        2         review              ,        punct          26
## 116        2       citizens              a          det          25
## 117        2         review       citizens        nsubj          26
## 118        2       separate          board        nsubj          33
## 119        2          board            and           cc          27
## 120        2     department             an          det          32
## 121        2     department       internal         amod          32
## 122        2     department        affairs     compound          32
## 123        2          board     department     conj:and          27
## 124        2       separate     department        nsubj          33
## 125        2         review       separate        xcomp          26
## 126        2     department           from         case          37
## 127        2     department            the          det          37
## 128        2     department         police     compound          37
## 129        2       separate     department   advcl:from          33
## 130        2     department              ,        punct          37
## 131        2          items          among         case          41
## 132        2          items          other         amod          41
## 133        2     department          items   nmod:among          37
## 134        2         review              .        punct          26
## 135        3           ROOT           said         root           0
## 136        3           said         colvin        nsubj           2
## 137        3           week           last         amod           4
## 138        3           said           week    nmod:tmod           2
## 139        3        meeting           that         dobj          17
## 140        3         school         orange         amod           8
## 141        3         school         street     compound           8
## 142        3         turned         school    nsubjpass          11
## 143        3         turned          would          aux          11
## 144        3         turned             be      auxpass          11
## 145        3           said         turned        ccomp           2
## 146        3         center           into         case          15
## 147        3         center              a          det          15
## 148        3         center      community     compound          15
## 149        3         turned         center    nmod:into          11
## 150        3         turned              ,        punct          11
## 151        3         turned        meeting        xcomp          11
## 152        3        meeting            one         dobj          17
## 153        3        demands             of         case          21
## 154        3        demands            the          det          21
## 155        3            one        demands      nmod:of          18
## 156        3           said              .        punct           2
## 157        4           ROOT           said         root           0
## 158        4        council            the          det           3
## 159        4        council           city     compound           3
## 160        4          plans        council        nsubj           5
## 161        4          plans           also       advmod           5
## 162        4           said          plans        ccomp          18
## 163        4        discuss             to         mark           7
## 164        4          plans        discuss        xcomp           5
## 165        4        discuss       creating        xcomp           7
## 166        4          board              a          det          11
## 167        4          board         review     compound          11
## 168        4       creating          board         dobj           8
## 169        4     department            for         case          15
## 170        4     department            the          det          15
## 171        4     department         police     compound          15
## 172        4       creating     department     nmod:for           8
## 173        4           said              ,        punct          18
## 174        4           said             he        nsubj          18
## 175        4           said              .        punct          18
## 176        5           ROOT           said         root           0
## 177        5           said            but           cc           7
## 178        5         monday             on         case           3
## 179        5           said         monday      nmod:on           7
## 180        5           said              ,        punct           7
## 181        5          mayor            the          det           6
## 182        5           said          mayor        nsubj           7
## 183        5           safe          mayor        nsubj          25
## 184        5     occupation            the          det           9
## 185        5           gone     occupation        nsubj          17
## 186        5       downtown             of         case          15
## 187        5       downtown            the          det          15
## 188        5       downtown         market     compound          15
## 189        5       downtown          house     compound          15
## 190        5       downtown           area     compound          15
## 191        5     occupation       downtown      nmod:of           9
## 192        5           gone            had          aux          17
## 193        5           said           gone        ccomp           7
## 194        5         enough             on       advmod          20
## 195        5         enough           long       advmod          20
## 196        5           gone         enough       advmod          17
## 197        5           said            and           cc           7
## 198        5           safe            was          cop          25
## 199        5         longer             no          neg          24
## 200        5           safe         longer       advmod          25
## 201        5           said           safe     conj:and           7
## 202        5  demonstrators            for         case          28
## 203        5  demonstrators            the          det          28
## 204        5           safe  demonstrators     nmod:for          25
## 205        5  demonstrators             or           cc          28
## 206        5           safe        members     nmod:for          25
## 207        5  demonstrators        members      conj:or          28
## 208        5         public             of         case          33
## 209        5         public            the          det          33
## 210        5  demonstrators         public      nmod:of          28
## 211        5           said              .        punct           7
## 212        6           ROOT           said         root           0
## 213        6            now          right       advmod           2
## 214        6           said            now       advmod          39
## 215        6         middle              ,        punct           8
## 216        6         middle           they        nsubj           8
## 217        6         middle            're          cop           8
## 218        6         middle             in         case           8
## 219        6         middle            the          det           8
## 220        6           said         middle    parataxis          39
## 221        6   intersection             of         case          12
## 222        6   intersection              a          det          12
## 223        6   intersection       four-way         amod          12
## 224        6         middle   intersection      nmod:of           8
## 225        6         circle             in         case          16
## 226        6         circle              a          det          16
## 227        6         circle        traffic     compound          16
## 228        6   intersection         circle      nmod:in          12
## 229        6         circle              ,        punct          16
## 230        6           safe          which        nsubj          22
## 231        6           safe             is          cop          22
## 232        6           safe     definitely       advmod          22
## 233        6           safe            not          neg          22
## 234        6         circle           safe    acl:relcl          16
## 235        6           them            for         case          24
## 236        6           safe           them     nmod:for          22
## 237        6   intersection             or           cc          12
## 238        6         middle         others      nmod:of           8
## 239        6   intersection         others      conj:or          12
## 240        6           come            who        nsubj          28
## 241        6         others           come    acl:relcl          26
## 242        6        support             to         mark          30
## 243        6           come        support        xcomp          28
## 244        6           come        support        xcomp          28
## 245        6        support        support     conj:and          30
## 246        6        support             or           cc          30
## 247        6           come           come        xcomp          28
## 248        6        support           come      conj:or          30
## 249        6             it             to         case          36
## 250        6             to            and           cc          33
## 251        6             to           from     conj:and          33
## 252        6        support             it      nmod:to          30
## 253        6        support             it    nmod:from          30
## 254        6         middle              ,        punct           8
## 255        6           said             he        nsubj          39
## 256        6           said              .        punct          39
## 257        7           ROOT           said         root           0
## 258        7         colvin    advertising     compound           2
## 259        7           said         colvin        nsubj           3
## 260        7        offered             he        nsubj           5
## 261        7           said        offered        ccomp           3
## 262        7  demonstrators            the          det           7
## 263        7        offered  demonstrators         iobj           5
## 264        7      locations        several         amod          10
## 265        7      locations    alternative         amod          10
## 266        7        offered      locations         dobj           5
## 267        7       continue          where       advmod          14
## 268        7       continue           they        nsubj          14
## 269        7       continue          could          aux          14
## 270        7      locations       continue    acl:relcl          10
## 271        7       exercise             to         mark          16
## 272        7       continue       exercise        xcomp          14
## 273        7          right          their    nmod:poss          18
## 274        7       exercise          right         dobj          16
## 275        7        protest             to         case          20
## 276        7       exercise        protest      nmod:to          16
## 277        7           said              ,        punct           3
## 278        7           said            but           cc           3
## 279        7         turned           they        nsubj          24
## 280        7           said         turned     conj:but           3
## 281        7         turned            him         dobj          24
## 282        7         turned           down compound:prt          24
## 283        7           said              .        punct           3
## 284        8           ROOT           said         root           0
## 285        8            end             at         case           3
## 286        8            end            the          det           3
## 287        8           said            end      nmod:at          17
## 288        8            day             of         case           6
## 289        8            day            the          det           6
## 290        8            end            day      nmod:of           3
## 291        8       priority              ,        punct          14
## 292        8         safety         public         amod           9
## 293        8       priority         safety        nsubj          14
## 294        8       priority             is          cop          14
## 295        8       priority            our    nmod:poss          14
## 296        8       priority            no.     compound          14
## 297        8       priority              1       nummod          14
## 298        8           said       priority    parataxis          17
## 299        8       priority              ,        punct          14
## 300        8           said             he        nsubj          17
## 301        8           said              .        punct          17
## 302        9           ROOT           know         root           0
## 303        9          chief            the          det           3
## 304        9          chief         police     compound           3
## 305        9           know          chief        nsubj          11
## 306        9          chief            and           cc           3
## 307        9       attorney            the          det           7
## 308        9       attorney           city     compound           7
## 309        9         office       attorney    nmod:poss           9
## 310        9       attorney             's         case           7
## 311        9          chief         office     conj:and           3
## 312        9           know         office        nsubj          11
## 313        9           know      basically       advmod          11
## 314        9             is           what         dobj          15
## 315        9            law            the          det          14
## 316        9             is            law        nsubj          15
## 317        9           know             is        ccomp          11
## 318        9      clarified             --        punct          19
## 319        9      clarified           they        nsubj          19
## 320        9      clarified            've          aux          19
## 321        9           know      clarified          dep          11
## 322        9      clarified           that         dobj          19
## 323        9      clarified             --        punct          19
## 324        9           know            and           cc          11
## 325        9         matter            now       advmod          30
## 326        9         matter             it        nsubj          30
## 327        9         matter             's          cop          30
## 328        9         matter           just       advmod          30
## 329        9         matter           like         case          30
## 330        9         matter            any          det          30
## 331        9         matter          other         amod          30
## 332        9           know         matter     conj:and          11
## 333        9     department           with         case          34
## 334        9     department            the          det          34
## 335        9     department         police     compound          34
## 336        9         matter     department    nmod:with          30
## 337        9           know              .        punct          11
## 338       10           ROOT        reached         root           0
## 339       10        reached         police    nsubjpass           8
## 340       10        hawkins          chief         amod           4
## 341       10        hawkins           gina     compound           4
## 342       10         police        hawkins          dep           1
## 343       10        reached          could          aux           8
## 344       10        reached            n't          neg           8
## 345       10        reached             be      auxpass           8
## 346       10        reached         monday    nmod:tmod           8
## 347       10        comment            for         case          11
## 348       10        reached        comment     nmod:for           8
## 349       10        removed             on         mark          23
## 350       10        removed           when       advmod          23
## 351       10           when            and           cc          13
## 352       10           when            how          dep          13
## 353       10     protesters            the          det          17
## 354       10        removed     protesters    nsubjpass          23
## 355       10     protesters            and           cc          17
## 356       10          tents          their    nmod:poss          20
## 357       10     protesters          tents     conj:and          17
## 358       10        removed          tents    nsubjpass          23
## 359       10        removed          would          aux          23
## 360       10        removed             be      auxpass          23
## 361       10        reached        removed        advcl           8
## 362       10        reached              .        punct           8
## 363       11           ROOT           said         root           0
## 364       11          jones       activist     compound           3
## 365       11          jones         rakeem     compound           3
## 366       11           said          jones        nsubj           4
## 367       11       campsite            the          det           6
## 368       11            way       campsite        nsubj          11
## 369       11            way             is          cop          11
## 370       11     protesters            the          det           9
## 371       11            way     protesters    nmod:poss          11
## 372       11     protesters              '         case           9
## 373       11           said            way        ccomp           4
## 374       11        helping             of         mark          13
## 375       11            way        helping          acl          11
## 376       11         public            the          det          15
## 377       11        helping         public         dobj          13
## 378       11        helping            and           cc          13
## 379       11            way        getting          acl          11
## 380       11        helping        getting     conj:and          13
## 381       11     acquainted         better       advmod          19
## 382       11        getting     acquainted        xcomp          17
## 383       11      stationed           with         mark          23
## 384       11       officers         police     compound          22
## 385       11      stationed       officers        nsubj          23
## 386       11     acquainted      stationed        ccomp          19
## 387       11      stationed         nearby       advmod          23
## 388       11           said              .        punct           4
## 389       12           ROOT           said         root           0
## 390       12      introduce             we        nsubj           2
## 391       12           said      introduce        ccomp           9
## 392       12      introduce      ourselves         dobj           2
## 393       12        officer             to         case           6
## 394       12        officer          every          det           6
## 395       12      introduce        officer      nmod:to           2
## 396       12           said              ,        punct           9
## 397       12           said          jones        nsubj           9
## 398       12           said              .        punct           9
## 399       13           ROOT           feed         root           0
## 400       13           feed           just       advmod           4
## 401       13           feed             as         mark           4
## 402       13           feed             we        nsubj           4
## 403       13           feed           feed        advcl          10
## 404       13         people          these          det           7
## 405       13         people       homeless         amod           7
## 406       13           feed         people         dobj           4
## 407       13           feed              ,        punct          10
## 408       13           feed             we        nsubj          10
## 409       13       officers            the          det          12
## 410       13           feed       officers         dobj          10
## 411       13           feed              .        punct          10
## 412       14           ROOT           give         root           0
## 413       14           give             we        nsubj           2
## 414       14           give           them         iobj           2
## 415       14           give          water         dobj           2
## 416       14          water            and           cc           4
## 417       14           give         drinks         dobj           2
## 418       14          water         drinks     conj:and           4
## 419       14           give              .        punct           2
## 420       15           ROOT           take         root           0
## 421       15           take             we        nsubj           2
## 422       15           take           care         dobj           2
## 423       15           them             of         case           5
## 424       15           care           them      nmod:of           3
## 425       15           take              .        punct           2
## 426       16           ROOT           take         root           0
## 427       16           take             we        nsubj           2
## 428       16           take           care         dobj           2
## 429       16      community             of         case           6
## 430       16      community            the          det           6
## 431       16           care      community      nmod:of           3
## 432       16           take              .        punct           2
## 433       17           ROOT          offer         root           0
## 434       17          offer        anybody    nmod:tmod           8
## 435       17          walks           that        nsubj           3
## 436       17        anybody          walks    acl:relcl           1
## 437       17          walks           past         dobj           3
## 438       17          walks           here       advmod           3
## 439       17          offer              ,        punct           8
## 440       17          offer             we        nsubj           8
## 441       17      something           them        nsubj          10
## 442       17          offer      something        xcomp           8
## 443       17          offer              .        punct           8
## 444       18           ROOT           said         root           0
## 445       18        talking       whenever       advmod           5
## 446       18          mayor            the          det           3
## 447       18        talking          mayor        nsubj           5
## 448       18        talking             is          aux           5
## 449       18           want        talking        advcl          14
## 450       18         issues          about         case           7
## 451       18        talking         issues   nmod:about           5
## 452       18         safety             of         case          10
## 453       18         safety         public         amod          10
## 454       18         issues         safety      nmod:of           7
## 455       18           want              ,        punct          14
## 456       18           want             we        nsubj          14
## 457       18           want         really       advmod          14
## 458       18           said           want        ccomp          28
## 459       18           want            him         dobj          14
## 460       18      recognize             to         mark          17
## 461       18           want      recognize        xcomp          14
## 462       18         issues            the          det          20
## 463       18         issues         actual         amod          20
## 464       18      recognize         issues         dobj          17
## 465       18         safety             of         case          23
## 466       18         safety         public         amod          23
## 467       18         issues         safety      nmod:of          20
## 468       18           said              ,        punct          28
## 469       18     benaveante       activist     compound          27
## 470       18     benaveante          mario     compound          27
## 471       18           said     benaveante        nsubj          28
## 472       18           said              .        punct          28
## 473       19           ROOT      brutality         root           0
## 474       19          issue            the          det           2
## 475       19      brutality          issue        nsubj           6
## 476       19      brutality             is          cop           6
## 477       19      brutality          about         case           6
## 478       19      brutality         police     compound           6
## 479       19      brutality            and           cc           6
## 480       19      incidents            all   det:predet          10
## 481       19      incidents          these          det          10
## 482       19      brutality      incidents     conj:and           6
## 483       19        rectify             we        nsubj          13
## 484       19        prevent             we        nsubj          15
## 485       19        rectify            can          aux          13
## 486       19      incidents        rectify    acl:relcl          10
## 487       19        rectify             or           cc          13
## 488       19      incidents        prevent    acl:relcl          10
## 489       19        rectify        prevent      conj:or          13
## 490       19      happening           from         mark          17
## 491       19      incidents      happening          acl          10
## 492       19      brutality              .        punct           6
## 493       20           ROOT          stood         root           0
## 494       20          house            the          det           3
## 495       20          house         market     compound           3
## 496       20          stood          house        nsubj           5
## 497       20          stood            has          aux           5
## 498       20           1832          since         case           7
## 499       20          stood           1832   nmod:since           5
## 500       20          stood              ,        punct           5
## 501       20          stood            and           cc           5
## 502       20         slaves           some          det          11
## 503       20           sold         slaves    nsubjpass          13
## 504       20           sold           were      auxpass          13
## 505       20          stood           sold     conj:and           5
## 506       20           sold          there       advmod          13
## 507       20            war         before         case          18
## 508       20            war            the          det          18
## 509       20            war          civil         amod          18
## 510       20           sold            war  nmod:before          13
## 511       20          stood              .        punct           5
## 512       21           ROOT          tried         root           0
## 513       21          tried        rioters        nsubj           2
## 514       21            set             to         mark           4
## 515       21          tried            set        xcomp           2
## 516       21            set             it         dobj           4
## 517       21           fire             on         case           7
## 518       21            set           fire      nmod:on           4
## 519       21            may             in         mark           9
## 520       21            set            may        advcl           4
## 521       21          tried              ,        punct           2
## 522       21          tried            and           cc           2
## 523       21          lives              a          det          14
## 524       21          lives          black         amod          14
## 525       21         matter          lives        nsubj          15
## 526       21          tried         matter     conj:and           2
## 527       21        painted          mural    nsubjpass          19
## 528       21        pain