社群媒體分析-期中專案

A.動機和分析目的

• 目的:使用coreNLP與sentimentr分析twitter上日本東京奧運的文字資料
• 概述:原訂於2020年舉辦的東京夏季奧運，因受全球新冠肺炎疫情影響，延至2021年舉辦。藉此利用推特的文章分析民眾對“日本東京奧運”的相關情緒。
• 資料來源:Twitter，4/10~4/17，5000筆，English

1. coreNLP

• 安裝JAVA JRE 1.8+ https://www.java.com/zh_TW/
• 下載Stanford coreNLP full模組

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("toyo2020.RData")

1.1 資料收集：tweets

(1). Twitter API設定 透過rtweet抓取tweets

app = 'heminghsin'
consumer_key = 'kjJGO9cTWdoCG9BHgBwfFtcfi'
consumer_secret = 'zjamiuhUuWZjjbsi01Jlg38uwVyXeQpiuFkUDk6QhiSIC379UO'
access_token = '1380751997343698949-qYevxQu1xqqP4dYegz4VeZUzSASi44'
access_secret = 'Lnbft6o7jK2Du8X9087qTFRRhs3UA2coYJSRi4KnrbR9d'
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("Japan")
context = "Olympics"
q = paste(c(key,context),collapse=" AND ")   
# 查詢字詞 "#EverGiven AND Suez"
# 為了避免只下#EverGiven 會找到非在suez中的tweets，加入Suez要同時出現的條件

#抓2000筆 不抓轉推
tweets = search_tweets(q,lang="en",n=2000,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)

##                                               
## 1 function (x, df1, df2, ncp, log = FALSE)    
## 2 {                                           
## 3     if (missing(ncp))                       
## 4         .Call(C_df, x, df1, df2, log)       
## 5     else .Call(C_dnf, x, df1, df2, ncp, log)
## 6 }

nrow(df)

## NULL

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

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("toyo2020.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)

• 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