基本介紹

1. coreNLP

安裝package

packages = c("dplyr","ggplot2","rtweet" ,"xml2", "httr", "jsonlite", "data.tree", "NLP", "igraph","sentimentr","tidytext","wordcloud2","DiagrammeR","dplyr")
existing = as.character(installed.packages()[,1])
for(pkg in packages[!(packages %in% existing)]) install.packages(pkg)
library(wordcloud2)
library(ggplot2)
library(scales)
library(rtweet)
library(dplyr)
library(xml2)
library(httr)
library(jsonlite)
library(magrittr)
library(data.tree)
library(tidytext)
library(stringr)
library(DiagrammeR)
library(magrittr)
load("coreNLP_all.RData")

1.1 資料收集：tweets

(1). Twitter API設定 透過rtweet抓取tweets

app = 'Emotions COVID-19 Vaccine'
consumer_key = 'sldS3M1c37owWAxx88lRg8anU'
consumer_secret = 'lCsUtxqA6DWC9nW7xH2a5KAITLXEX8oj10tcWE7zRVTxgHARfC'
access_token = '1283052584312410112-LocNkHahyAJ50KR0sADTmHryO0k3Kq'
access_secret = 'gLssR17xxOZUDLeiF6sB5LiwSYAAVBE0mLjXQolINF4k3'
twitter_token <- create_token(app,consumer_key, consumer_secret,
                    access_token, access_secret,set_renv = FALSE)
#Consumer Keys:知道你的身分
#Authentication Tokens:認證給你的授權

(2). 設定關鍵字抓tweets

# 查詢關鍵字
key = c("#COVID-19")
context = "Vaccine"
q = paste(c(key,context),collapse=" AND ")   
# 查詢字詞 "#COVID-19 AND Vaccine"
# 為了避免只下#COVID-19 會找到非在Vaccine中的tweets，加入Vaccine要同時出現的條件

#抓5000筆 不抓轉推
tweets = search_tweets(q,lang="en",n=5000,include_rts = FALSE,token = twitter_token)

(3). tweets內容清理

## 用於資料清理
clean = function(txt) {
  txt = iconv(txt, "latin1", "ASCII", sub="") #改變字的encoding
  txt = gsub("(@|#)\\w+", "", txt) #去除@或#後有數字,字母,底線 (標記人名或hashtag)
  txt = gsub("(http|https)://.*", "", txt) #去除網址(.:任意字元，*:0次以上)
  txt = gsub("[ \t]{2,}", "", txt) #去除兩個以上空格或tab
  txt = gsub("\\n"," ",txt) #去除換行
  txt = gsub("\\s+"," ",txt) #去除一個或多個空格(+:一次以上)
  txt = gsub("^\\s+|\\s+$","",txt) #去除開頭/結尾有一個或多個空格
  txt = gsub("&.*;","",txt) #去除html特殊字元編碼
  txt = gsub("[^a-zA-Z0-9?!. ']","",txt) #除了字母,數字空白?!.的都去掉(表情符號去掉)
  txt }


tweets$text = clean(tweets$text)  #text套用資料清理

df = data.frame()
  
df = rbind(df,tweets)  # transfer to data frame

df = df[!duplicated(df[,"status_id"]),]  #去除重複的tweets
head(df)
## # A tibble: 6 x 90
##   user_id   status_id   created_at          screen_name  text            source 
##   <chr>     <chr>       <dttm>              <chr>        <chr>           <chr>  
## 1 22160419~ 1380839997~ 2021-04-10 11:08:04 MarshallProj While more tha~ Social~
## 2 13667952~ 1380839945~ 2021-04-10 11:07:52 kcvaccinewa~ KS Vaccine app~ KC Vac~
## 3 13667952~ 1380751600~ 2021-04-10 05:16:49 kcvaccinewa~ MO Vaccine app~ KC Vac~
## 4 13667952~ 1380839936~ 2021-04-10 11:07:50 kcvaccinewa~ KS Vaccine app~ KC Vac~
## 5 13667952~ 1380675347~ 2021-04-10 00:13:49 kcvaccinewa~ MO Vaccine app~ KC Vac~
## 6 13667952~ 1380680897~ 2021-04-10 00:35:52 kcvaccinewa~ MO Vaccine app~ KC Vac~
## # ... with 84 more variables: display_text_width <dbl>,
## #   reply_to_status_id <chr>, reply_to_user_id <chr>,
## #   reply_to_screen_name <chr>, is_quote <lgl>, is_retweet <lgl>,
## #   favorite_count <int>, retweet_count <int>, quote_count <int>,
## #   reply_count <int>, hashtags <list>, symbols <list>, urls_url <list>,
## #   urls_t.co <list>, urls_expanded_url <list>, media_url <list>,
## #   media_t.co <list>, media_expanded_url <list>, media_type <list>,
## #   ext_media_url <list>, ext_media_t.co <list>, ext_media_expanded_url <list>,
## #   ext_media_type <chr>, mentions_user_id <list>, mentions_screen_name <list>,
## #   lang <chr>, quoted_status_id <chr>, quoted_text <chr>,
## #   quoted_created_at <dttm>, quoted_source <chr>, quoted_favorite_count <int>,
## #   quoted_retweet_count <int>, quoted_user_id <chr>, quoted_screen_name <chr>,
## #   quoted_name <chr>, quoted_followers_count <int>,
## #   quoted_friends_count <int>, quoted_statuses_count <int>,
## #   quoted_location <chr>, quoted_description <chr>, quoted_verified <lgl>,
## #   retweet_status_id <chr>, retweet_text <chr>, retweet_created_at <dttm>,
## #   retweet_source <chr>, retweet_favorite_count <int>,
## #   retweet_retweet_count <int>, retweet_user_id <chr>,
## #   retweet_screen_name <chr>, retweet_name <chr>,
## #   retweet_followers_count <int>, retweet_friends_count <int>,
## #   retweet_statuses_count <int>, retweet_location <chr>,
## #   retweet_description <chr>, retweet_verified <lgl>, place_url <chr>,
## #   place_name <chr>, place_full_name <chr>, place_type <chr>, country <chr>,
## #   country_code <chr>, geo_coords <list>, coords_coords <list>,
## #   bbox_coords <list>, status_url <chr>, name <chr>, location <chr>,
## #   description <chr>, url <chr>, protected <lgl>, followers_count <int>,
## #   friends_count <int>, listed_count <int>, statuses_count <int>,
## #   favourites_count <int>, account_created_at <dttm>, verified <lgl>,
## #   profile_url <chr>, profile_expanded_url <chr>, account_lang <lgl>,
## #   profile_banner_url <chr>, profile_background_url <chr>,
## #   profile_image_url <chr>

df共有90個欄位，但我們在這裡僅會使用幾個欄位:

  • user_id: 用戶id
  • status_id : 推文id
  • created_at : 發文時間
  • text : 推文內容
  • source : 發文來源

了解資料的資料筆數以及時間分布

created_at已經是一個date類型的欄位，因此可以直接用min,max來看最遠或最近的日期
註:rtweet最多只能抓到距今10天的資料

nrow(df)
## [1] 4961
min(df$created_at)
## [1] "2021-04-09 23:43:23 UTC"
max(df$created_at)
## [1] "2021-04-10 11:08:04 UTC"

1-2串接CoreNLP API

(1). API呼叫的設定

server端 : + 需先在terminal開啟corenlp server + 在corenlp的路徑下開啟terminal輸入 java -mx4g -cp "*" edu.stanford.nlp.pipeline.StanfordCoreNLPServer -port 9000 -timeout 15000

# 產生coreNLP的api url，將本地端的網址轉成符合coreNLP服務的url
generate_API_url <- function(host, port="9000",
                    tokenize.whitespace="false", annotators=""){ #斷詞依據不是空格
    url <- sprintf('http://%s:%s/?properties={"tokenize.whitespace":"%s","annotators":"%s"}', host, port, tokenize.whitespace, annotators)
    url <- URLencode(url)
}
#指定服務的位置
host = "127.0.0.1"

generate_API_url(host)
# 呼叫coreNLP api
call_coreNLP <- function(server_host, text, host="localhost", language="eng",
                    tokenize.whitespace="true", ssplit.eolonly="true", annotators=c("tokenize","ssplit","pos","lemma","ner","parse","sentiment")){
  # 假設有兩個core-nlp server、一個負責英文（使用9000 port）、另一個則負責中文（使用9001 port）
  port <- ifelse(language=="eng", 9000, 9001);
  # 產生api網址
  url <- generate_API_url(server_host, port=port,
                    tokenize.whitespace=tokenize.whitespace, annotators=paste0(annotators, collapse = ','))
  
  result <- POST(url, body = text, encode = "json")
  doc <- httr::content(result, "parsed","application/json",encoding = "UTF-8")
  return (doc)
}
#文件使用coreNLP服務
coreNLP <- function(data,host){
  # 依序將每個文件丟進core-nlp進行處理，每份文件的回傳結果為json格式
  # 在R中使用objects來儲存處理結果
  result <- apply(data, 1 , function(x){
    object <- call_coreNLP(host, x['text'])
    list(doc=object, data=x)
  })
  
  return(result)
}

(2). 資料整理function

從回傳的object中整理斷詞出結果，輸出為 tidydata 格式

coreNLP_tokens_parser <- function(coreNLP_objects){
  
  result <- do.call(rbind, lapply(coreNLP_objects, function(obj){
    original_data <- obj$data
    doc <- obj$doc
    # for a sentences
    sentences <- doc$sentences
   
    sen <- sentences[[1]]
    
    tokens <- do.call(rbind, lapply(sen$tokens, function(x){
      result <- data.frame(word=x$word, lemma=x$lemma, pos=x$pos, ner=x$ner)
      result
    }))
    
    tokens <- original_data %>%
      t() %>% 
      data.frame() %>% 
      select(-text) %>% 
      slice(rep(1:n(), each = nrow(tokens))) %>% 
      bind_cols(tokens)
    
    tokens
  }))
  return(result)
}

從回傳的core-nlp object中整理出詞彙依存關係，輸出為 tidydata 格式

coreNLP_dependency_parser <- function(coreNLP_objects){
  result <- do.call(rbind, lapply(coreNLP_objects, function(obj){
    original_data <- obj$data
    doc <- obj$doc
    # for a sentences
    sentences <- doc$sentences
    sen <- sentences[[1]]
    dependencies <- do.call(rbind, lapply(sen$basicDependencies, function(x){
      result <- data.frame(dep=x$dep, governor=x$governor, governorGloss=x$governorGloss, dependent=x$dependent, dependentGloss=x$dependentGloss)
      result
    }))
  
    dependencies <- original_data %>%
      t() %>% 
      data.frame() %>% 
      select(-text) %>% 
      slice(rep(1:n(), each = nrow(dependencies))) %>% 
      bind_cols(dependencies)
    dependencies
  }))
  return(result)
}

從回傳的core-nlp object中整理出語句情緒，輸出為 tidydata 格式

coreNLP_sentiment_parser <- function(coreNLP_objects){
  result <- do.call(rbind, lapply(coreNLP_objects, function(obj){
    original_data <- obj$data
    doc <- obj$doc
    # for a sentences
    sentences <- doc$sentences
    sen <- sentences[[1]]
    
    sentiment <- original_data %>%
      t() %>% 
      data.frame() %>% 
      bind_cols(data.frame(sentiment=sen$sentiment, sentimentValue=sen$sentimentValue))
  
    sentiment
  }))
  return(result)
}

圖形化 Dependency tree

程式參考來源：https://stackoverflow.com/questions/35496560/how-to-convert-corenlp-generated-parse-tree-into-data-tree-r-package

# 圖形化顯示dependency結果
parse2tree <- function(ptext) {
  stopifnot(require(NLP) && require(igraph))
  
  # this step modifies coreNLP parse tree to mimic openNLP parse tree
  ptext <- gsub("[\r\n]", "", ptext)
  ptext <- gsub("ROOT", "TOP", ptext)


  ## Replace words with unique versions
  ms <- gregexpr("[^() ]+", ptext)                                      # just ignoring spaces and brackets?
  words <- regmatches(ptext, ms)[[1]]                                   # just words
  regmatches(ptext, ms) <- list(paste0(words, seq.int(length(words))))  # add id to words
  
  ## Going to construct an edgelist and pass that to igraph
  ## allocate here since we know the size (number of nodes - 1) and -1 more to exclude 'TOP'
  edgelist <- matrix('', nrow=length(words)-2, ncol=2)
  
  ## Function to fill in edgelist in place
  edgemaker <- (function() {
    i <- 0                                       # row counter
    g <- function(node) {                        # the recursive function
      if (inherits(node, "Tree")) {            # only recurse subtrees
        if ((val <- node$value) != 'TOP1') { # skip 'TOP' node (added '1' above)
          for (child in node$children) {
            childval <- if(inherits(child, "Tree")) child$value else child
            i <<- i+1
            edgelist[i,1:2] <<- c(val, childval)
          }
        }
        invisible(lapply(node$children, g))
      }
    }
  })()
  
  ## Create the edgelist from the parse tree
  edgemaker(Tree_parse(ptext))
  tree <- FromDataFrameNetwork(as.data.frame(edgelist))
  return (tree)
}

將句子丟入服務

取得coreNLP回傳的物件
先不要跑這段，會花大概半小時（如果你記憶體只有4G可能會當掉）

#gc() #釋放不使用的記憶體

#t0 = Sys.time()
#obj = df[,c(2,5)]  %>% filter(text != "") %>% coreNLP(host) #丟入本地執行
#丟入coreNLP的物件 必須符合: 是一個data.frame 有一個text欄位

#Sys.time() - t0 #執行時間
#Time difference of 28 mins

#save.image("coreNLP_covid19.RData")
#先將會用到的東西存下來，要用可直接載RData
#tokens =  coreNLP_tokens_parser(obj)
#dependencies = coreNLP_dependency_parser(obj)
#sentiment = coreNLP_sentiment_parser(obj)
#save.image("coreNLP_all.RData")

1-3 提取結果

(1). 斷詞、詞彙還原、詞性標註、NER

tokens =  coreNLP_tokens_parser(obj)
head(tokens,20)
##              status_id        word       lemma pos ner
## 1  1380839997042008067       While       while  IN   O
## 2  1380839997042008067        more        more JJR   O
## 3  1380839997042008067        than        than  IN   O
## 4  1380839997042008067        half        half PDT   O
## 5  1380839997042008067         the         the  DT   O
## 6  1380839997042008067     country     country  NN   O
## 7  1380839997042008067         has        have VBZ   O
## 8  1380839997042008067      opened        open VBN   O
## 9  1380839997042008067          up          up  RP   O
## 10 1380839997042008067     COVID19     covid19  NN   O
## 11 1380839997042008067     vaccine     vaccine  NN   O
## 12 1380839997042008067 eligibility eligibility  NN   O
## 13 1380839997042008067   prisoners    prisoner NNS   O
## 14 1380839997042008067       still       still  RB   O
## 15 1380839997042008067        lack        lack VBP   O
## 16 1380839997042008067      access      access  NN   O
## 17 1380839997042008067          to          to  IN   O
## 18 1380839997042008067        them        they PRP   O
## 19 1380839997042008067          on          on  IN   O
## 20 1380839997042008067         the         the  DT   O
  • coreNLP_tokens_parser欄位:
    • status_id : 對應原本df裡的status_id，為一則tweets的唯一id
    • word: 原始斷詞
    • lemma : 對斷詞做詞形還原
    • pos : part-of-speech,詞性
    • ner: 命名實體

(2). 命名實體標註(NER)

  • 從NER查看特定類型的實體，辨識出哪幾種類型
unique(tokens$ner)
##  [1] "O"                 "NUMBER"            "STATE_OR_PROVINCE"
##  [4] "ORGANIZATION"      "DURATION"          "DATE"             
##  [7] "LOCATION"          "CITY"              "PERSON"           
## [10] "CAUSE_OF_DEATH"    "MISC"              "COUNTRY"          
## [13] "IDEOLOGY"          "ORDINAL"           "PERCENT"          
## [16] "TITLE"             "NATIONALITY"       "TIME"             
## [19] "CRIMINAL_CHARGE"   "SET"               "RELIGION"         
## [22] "MONEY"             "URL"
#除去entity為Other，有多少種word有被標註entity
length(unique(tokens$word[tokens$ner != "O"])) 
## [1] 3666

(3). 轉小寫

因為大小寫也會影響corenlp對NER的判斷，因此我們一開始給的推文內容是沒有處理大小寫的，但在跑完anotator後，為了正確計算詞頻，創建新欄位lower_word與lower_lemma，存放轉換小寫的word與lemma。轉成小寫的目的是要將不同大小寫的同一字詞（如Evergiven與evergiven）都換成小寫，再來計算詞頻

tokens$lower_word = tolower(tokens$word)
tokens$lower_lemma = tolower(tokens$lemma)

1.4 探索分析 - NER

涉及到的國家(COUNTRY)

我們可以透過coreNLP中的NER解析出在Twitter上面談論covid19疫苗的事情，所涉及到的國家(COUNTRY)，以初步了解這個議題的主要國家。

tokens %>%
  filter(ner == "COUNTRY") %>%  #篩選NER為COUNTRY
  group_by(lower_word) %>% #根據word分組
  summarize(count = n()) %>% #計算每組
  top_n(n = 13, count) %>%
  ungroup() %>% 
  mutate(word = reorder(lower_word, count)) %>%
  ggplot(aes(word, count)) + 
  geom_col()+
  ggtitle("Word Frequency (NER is COUNTRY)") +
  theme(text=element_text(size=14))+
  coord_flip()

  • 討論最多的國家是india
涉及到的組織(ORGANIZATION)

我們可以透過coreNLP中的NER解析出在Twitter上面談論covid19疫苗的事情，所涉及到的組織(ORGANIZATION)，以初步了解這個議題的主要公司/單位。

tokens %>%
  filter(ner == "ORGANIZATION") %>%  #篩選NER為ORGANIZATION
  group_by(lower_word) %>% #根據word分組
  summarize(count = n()) %>% #計算每組
  top_n(n = 10, count) %>%
  ungroup() %>% 
  mutate(word = reorder(lower_word, count)) %>%
  ggplot(aes(word, count)) + 
  geom_col()+
  ggtitle("Word Frequency (NER is ORGANIZATION)") +
  theme(text=element_text(size=14))+
  coord_flip()

  • pfizer 輝瑞公司，是一家總部位於美國紐約的跨國製藥、生物技術公司，研發總部位於康乃狄克州的格羅頓市。根據收入排名，輝瑞是全球最大的製藥公司。
  • walgreensduane reade 杜安里德 (Duane Reade)是Walgreens Boots Alliance旗下的一家連鎖藥店和便利店。
  • cvs CVS藥局是美國的一家藥妝店連鎖企業，也是美國最大的藥妝店連鎖企業，
涉及到的人物(PERSON)

我們可以透過coreNLP中的NER解析出在Twitter上面談論covid19疫苗的事情，所涉及到的人物(PERSON)，以初步了解這個議題的主要人物。

tokens %>%
  filter(ner == "PERSON") %>%  #篩選NER為PERSON
  group_by(lower_word) %>% #根據word分組
  summarize(count = n()) %>% #計算每組
  top_n(n = 10, count) %>%
  ungroup() %>% 
  mutate(word = reorder(lower_word, count)) %>%
  ggplot(aes(word, count)) + 
  geom_col()+
  ggtitle("Word Frequency (NER is PERSON)") +
  theme(text=element_text(size=14))+
  coord_flip()

  • johnson:

1.5 探索分析 - Dependency

語句依存關係結果
dependencies = coreNLP_dependency_parser(obj)
head(dependencies,20)
##              status_id          dep governor governorGloss dependent
## 1  1380839997042008067         ROOT        0          ROOT        15
## 2  1380839997042008067         mark        8        opened         1
## 3  1380839997042008067       advmod        4          half         2
## 4  1380839997042008067        fixed        2          more         3
## 5  1380839997042008067       nummod        6       country         4
## 6  1380839997042008067          det        6       country         5
## 7  1380839997042008067        nsubj        8        opened         6
## 8  1380839997042008067          aux        8        opened         7
## 9  1380839997042008067        csubj       15          lack         8
## 10 1380839997042008067 compound:prt        8        opened         9
## 11 1380839997042008067     compound       13     prisoners        10
## 12 1380839997042008067     compound       12   eligibility        11
## 13 1380839997042008067     compound       13     prisoners        12
## 14 1380839997042008067          obj        8        opened        13
## 15 1380839997042008067       advmod       15          lack        14
## 16 1380839997042008067          obj       15          lack        16
## 17 1380839997042008067         case       18          them        17
## 18 1380839997042008067         nmod       16        access        18
## 19 1380839997042008067         case       22         Fewer        19
## 20 1380839997042008067          det       22         Fewer        20
##    dependentGloss
## 1            lack
## 2           While
## 3            more
## 4            than
## 5            half
## 6             the
## 7         country
## 8             has
## 9          opened
## 10             up
## 11        COVID19
## 12        vaccine
## 13    eligibility
## 14      prisoners
## 15          still
## 16         access
## 17             to
## 18           them
## 19             on
## 20            the
視覺化 Dependency tree
parse_tree <- obj[[113]]$doc[[1]][[1]]$parse
tree <- parse2tree(parse_tree)
SetNodeStyle(tree, style = "filled,rounded", shape = "box")
plot(tree)

1.6 探索分析 - Sentiment

語句情緒值

情緒分數從最低分0~最高分4
+ 0,1 : very negative,negative
+ 2 : neutral
+ 3,4 : very positive,postive

sentiment = coreNLP_sentiment_parser(obj)
head(sentiment,20)
##              status_id
## 1  1380839997042008067
## 2  1380839945443627009
## 3  1380751600227119105
## 4  1380839936795025409
## 5  1380675347415511040
## 6  1380680897733726215
## 7  1380675872353619972
## 8  1380675870914908161
## 9  1380751362070351872
## 10 1380680384548114434
## 11 1380786700985716738
## 12 1380681152642609158
## 13 1380831556487553027
## 14 1380751602953379841
## 15 1380839444979326979
## 16 1380693467249180674
## 17 1380751601678364672
## 18 1380839432924901377
## 19 1380675869253992450
## 20 1380777640441876481
##                                                                                                                                                                                                                                                        text
## 1  While more than half the country has opened up COVID19 vaccine eligibility prisoners still lack access to them on the whole. Fewer than 20 of state and federal prisoners have been vaccinated according to data collected by The Marshall Project and .
## 2                                                                                                                                                                                    KS Vaccine appointments available at CVS Prairie Village. Sign up here
## 3                                                                                                                                             MO Vaccine appointments available at Walgreens Kansas City from Apr 11 to Apr 14. Sign up here zip code 64110
## 4                                                                                                                                                                                        KS Vaccine appointments available at CVS Kansas City. Sign up here
## 5                                                                                                                                             MO Vaccine appointments available at Walgreens Kansas City from Apr 10 to Apr 14. Sign up here zip code 64110
## 6                                                                                                                                                 MO Vaccine appointments available at Walgreens Raytown from Apr 10 to Apr 14. Sign up here zip code 64133
## 7                                                                                                                                             MO Vaccine appointments available at Walgreens Kansas City from Apr 10 to Apr 14. Sign up here zip code 64110
## 8                                                                                                                                            MO Vaccine appointments available at Walgreens Independence from Apr 10 to Apr 14. Sign up here zip code 64052
## 9                                                                                                                                                         MO Vaccine appointments available at Walgreens Kansas City on Apr 13. Sign up here zip code 64119
## 10                                                                                                                                            MO Vaccine appointments available at Walgreens Kansas City from Apr 10 to Apr 14. Sign up here zip code 64128
## 11                                                                                                                                                                                   KS Vaccine appointments available at CVS Prairie Village. Sign up here
## 12                                                                                                                                            MO Vaccine appointments available at Walgreens Kansas City from Apr 10 to Apr 14. Sign up here zip code 64110
## 13                                                                                                                                                                                       KS Vaccine appointments available at CVS Kansas City. Sign up here
## 14                                                                                                                                            MO Vaccine appointments available at Walgreens Kansas City from Apr 12 to Apr 14. Sign up here zip code 64110
## 15                                                                                                                                                                                   KS Vaccine appointments available at CVS Prairie Village. Sign up here
## 16                                                                                                                                            MO Vaccine appointments available at Walgreens Kansas City from Apr 10 to Apr 14. Sign up here zip code 64110
## 17                                                                                                                                            MO Vaccine appointments available at Walgreens Kansas City from Apr 11 to Apr 14. Sign up here zip code 64128
## 18                                                                                                                                                                                       KS Vaccine appointments available at CVS Kansas City. Sign up here
## 19                                                                                                                                              MO Vaccine appointments available at Walgreens Grandview from Apr 10 to Apr 14. Sign up here zip code 64030
## 20                                                                                                                                            MO Vaccine appointments available at Walgreens Kansas City from Apr 11 to Apr 14. Sign up here zip code 64128
##    sentiment sentimentValue
## 1   Negative              1
## 2    Neutral              2
## 3    Neutral              2
## 4    Neutral              2
## 5    Neutral              2
## 6    Neutral              2
## 7    Neutral              2
## 8    Neutral              2
## 9    Neutral              2
## 10   Neutral              2
## 11   Neutral              2
## 12   Neutral              2
## 13   Neutral              2
## 14   Neutral              2
## 15   Neutral              2
## 16   Neutral              2
## 17   Neutral              2
## 18   Neutral              2
## 19   Neutral              2
## 20   Neutral              2
資料集中的情緒種類
unique(sentiment$sentiment)
## [1] "Negative"     "Neutral"      "Positive"     "Verypositive" "Verynegative"
sentiment$sentimentValue = sentiment$sentimentValue %>% as.numeric
#了解情緒文章的分佈
sentiment$sentiment %>% table()
## .
##     Negative      Neutral     Positive Verynegative Verypositive 
##         1120         3224          575            1            3
平均情緒分數時間趨勢
df$date = as.Date(df$created_at)

sentiment %>% 
  merge(df[,c("status_id","source","date")]) %>%
  group_by(date) %>% 
  summarise(avg_sentiment = mean(sentimentValue,na.rm=T)) %>% 
  ggplot(aes(x=date,y=avg_sentiment)) + 
  geom_line()

不同用戶端情緒時間趨勢
sentiment %>% 
  merge(df[,c("status_id","source","date")]) %>%
  filter(source %in% c("Twitter Web Client","Twitter for iPhone","Twitter for Android")) %>% 
  group_by(date,source) %>% 
  summarise(avg_sentiment = mean(sentimentValue,na.rm=T)) %>% 
  ggplot(aes(x=date,y=avg_sentiment,color=source)) + 
  geom_line()
## `summarise()` has grouped output by 'date'. You can override using the `.groups` argument.

了解情緒分佈，以及在正面情緒及負面情緒下，所使用的文章詞彙為何?
#了解正面文章的詞彙使用
sentiment %>% 
  merge(tokens) %>% 
  anti_join(stop_words) %>% 
  filter(!lower_word %in% c('i','the','covid19')) %>% 
  filter(sentiment == "Verypositive" | sentiment =='Positive') %>%
  group_by(lower_lemma) %>% #根據lemma分組
  summarize(count = n()) %>% 
  filter(count >5 & count<400)%>%
  wordcloud2()
## Joining, by = "word"
#了解負面文章的詞彙使用
sentiment %>% 
  merge(tokens) %>% 
  anti_join(stop_words) %>% 
  filter(!lower_word %in% c('i','the')) %>% 
  filter(sentiment == "Verynegative" | sentiment =='Negative') %>%
  group_by(lower_lemma) %>% 
  summarize(count = n()) %>% 
  filter(count >10 &count<400)%>%
  wordcloud2()

“wordcloud”

2. Sentimentr 英文情緒分析

library(sentimentr)
## Warning: package 'sentimentr' was built under R version 4.0.5
mytext <- c(
    "I heard you on the phone, I had you in mind",
    "I've been on the run since you walked through the hallway",
    "Heard it all before, I don't even mind",
    "I'll do anything, pull me in and I'm far away"
)

mytext <- get_sentences(mytext) #物件，將character向量轉成list,list裡放著character向量(已斷句)
每個文本的情緒分數

情緒分數為-1~1之間，<0屬於負面，>0屬於正面，0屬於中性

sentiment_by(mytext) #document level
##    element_id word_count sd ave_sentiment
## 1:          1         11 NA             0
## 2:          2         11 NA             0
## 3:          3          8 NA             0
## 4:          4         10 NA             0
每個句子的情緒分數
sentiment(mytext) #sentence level
##    element_id sentence_id word_count sentiment
## 1:          1           1         11         0
## 2:          2           1         11         0
## 3:          3           1          8         0
## 4:          4           1         10         0
  • 回傳4個欄位的dataframe:
    • element_id – 第幾個文本
    • sentence_id – 該文本中的第幾個句子
    • word_count – 句子字數
    • sentiment – 句子的情緒分數

2.2 使用twitter資料實踐在sentimentr

計算tweet中屬於正面的字
set.seed(10)
mytext <- get_sentences(tweets$text) #將text轉成list of characters型態
x <- sample(tweets$text, 1000, replace = FALSE) #隨機取1000筆，取後不放回
sentiment_words <- extract_sentiment_terms(x) #抓取其中帶有情緒的字
sentiment_counts <- attributes(sentiment_words)$counts #計算出現次數
sentiment_counts[polarity > 0,]   #正面的字
##            words polarity  n
##   1:    approval      1.0 18
##   2:      please      1.0 10
##   3:    efficacy      1.0  9
##   4:        care      1.0  5
##   5:    approved      1.0  5
##  ---                        
## 370:      prefer      0.1  1
## 371: cooperation      0.1  1
## 372:       peaks      0.1  1
## 373:       novel      0.1  1
## 374:        pray      0.1  1
計算tweet中屬於負面的字
sentiment_counts[polarity < 0,] %>% arrange(desc(n)) %>% top_n(10) #出現次數最多的負面字
## Selecting by n
##          words polarity  n
##  1:       shot    -0.40 32
##  2:   declined    -0.60 24
##  3:     crisis    -0.75 22
##  4:  emergency    -0.75 21
##  5:   pandemic    -1.00 18
##  6:        jab    -0.60 16
##  7:       risk    -0.75 16
##  8: government    -0.50 15
##  9:   shortage    -0.75 15
## 10:      virus    -0.50 12
## 11:    adverse    -0.50 12
highlight每個句子，判斷屬於正/負面
set.seed(12)
df%>%
    filter(status_id %in% sample(unique(status_id), 30)) %>% #隨機30筆貼文
    mutate(review = get_sentences(text)) %$% 
    sentiment_by(review, status_id) %>%
    highlight()
## Saved in C:\Users\ASUS-NB\AppData\Local\Temp\RtmpsLmuJa/polarity.html
## Opening C:\Users\ASUS-NB\AppData\Local\Temp\RtmpsLmuJa/polarity.html ...

2.3 用日期來了解情緒波動

code 參考 https://github.com/trinker/sentimentr

tweets$date = format(tweets$created_at,'%Y%m%d')

(out  = tweets  %>%  with(
    sentiment_by( #document level
        get_sentences(text), 
        list( date)
    )
))
plot(out)

2.4 用日期來了解不同用戶端情的緒波動

(out  = tweets %>% filter(source %in% c("Twitter Web Client","Twitter for iPhone","Twitter for Android")) %>%  with(
    sentiment_by(
        get_sentences(text), 
        list(source, date)
    )
))
plot(out)

轉換Emoji代碼為語意文字
replace_emoji("\U0001f4aa")
## [1] " flexed biceps "