情感分析R

Question

[我想使用R在Twitter上的推文进行情感分析。R中有任何方法。我为Analysis选择软件包tm。我安装了所需的软件包，并在推文中搜索特定主题。然后我保存数据并制作一个语料库。然后清除数据以进行分析。

mycorpus<-Corpus(VectorSource(tweets_df$text))

removeURL<-function(x) gsub("http[:alnum:]*","",x)
removeNumPunct<-function(x) gsub("[^[:alpha:][:space:]]*","",x)
removeUsername <- function(x) gsub('@[^[:space:]]*', '', x)

mycorpus<-tm_map(mycorpus,PlainTextDocument)
mycorpus <- tm_map(mycorpus, content_transformer(removeUsername))
mycorpus<-tm_map(mycorpus,content_transformer(removeURL))
mycorpus<-tm_map(mycorpus,content_transformer(tolower))
mycorpus <- tm_map(mycorpus, content_transformer(removeNumPunct)) 
mycorpus <- tm_map(mycorpus, removeNumbers)
mycorpus<-tm_map(mycorpus,stripWhitespace)
Stopwords <- readLines("/Users/Desktop/Stopwords.txt")
mycorpus <- tm_map(mycorpus, function(x) removeWords(x, germanStopwords))

在完成干净步骤后，我创建了一个文档术语矩阵和一个词云。到目前为止，我还没有问题或错误消息。

tweets_dtm <- DocumentTermMatrix(mycorpus)
tweets_dtm 

对于情感分数，我进行以下步骤。

score.sentiment = function(Tweets, positivwords, negativwords, progress='none'){
    scores = laply(Tweets, 
                      function(Tweets, positivwords, negativwords) {
                      Tweets = gsub('[[:punct:]]', '', Tweets) # removes punctuation 
                      Tweets = gsub('[[:cntrl:]]', '', Tweets) # removes controlcharacters
                      Tweets = gsub('\\d+', '', Tweets) # removes numbers     
                      Tweets = gsub('https://', '', Tweets) # removes https:// 
                      Tweets = gsub('http://', '', Tweets) # removes http://
                      Tweets = gsub('[^[:graph:]]', '', Tweets) # removes graphic            characters like emoticons

                                 tryTolower=function(x){ 
                                         y - NA

                                              try_error=tryCatch(tolower(x),error=function(e)e)

                                  if(inherits(try_error,"error"))
                                             y - tolower (x)

                                                return(y)
                                  }

                Tweets=sapply (Tweets, tryTolower)
                word_list = str_split(Tweets, '\\s+') # splits the tweets by word in a list
                    words = unlist(word_list) # turns the list into vector





 positive.matches = match(words, positivwords) ## returns matching 
  negative.matches = match(words, negativwords)

 positive_matches = !is.na(positive.matches) ## converts matching values to true of false
negative_matches = !is.na(negative.matches)

       score = sum(positive_matches) - sum(negative_matches) # true and false are 

                         return(score)

                            }, positive_matches, negative_matches, .progress -.progress )
   return(score)
      }

直到这里我没有错误消息。现在，我将以下代码用于推文的情感评分：

score <- score.sentiment(tweets,positivwords,negativwords, .progress='text')
tweets$score=score

但是我有以下错误信息

score.sentiment（税，正词，负词，.progress =“ text”）中的错误： 未使用的参数（.progress =“ text”）

什么是此错误消息？

Answer 1

您为函数progress而不是.progress命名了参数，这就是为什么函数无法识别参数的原因。您还输了第二行的lapply（您写了laply）。所以这应该工作：

score.sentiment = function(Tweets, positivwords, negativwords, .progress='none'){ #changed progress to .progress
  scores = lapply(Tweets, #changed laply to lapply
                 function(Tweets, positivwords, negativwords) {
                   Tweets = gsub('[[:punct:]]', '', Tweets) # removes punctuation 
                   Tweets = gsub('[[:cntrl:]]', '', Tweets) # removes controlcharacters
                   Tweets = gsub('\\d+', '', Tweets) # removes numbers     
                   Tweets = gsub('https://', '', Tweets) # removes https:// 
                   Tweets = gsub('http://', '', Tweets) # removes http://
                   Tweets = gsub('[^[:graph:]]', '', Tweets) # removes graphic            characters like emoticons

                   tryTolower=function(x){ 
                     y - NA

                     try_error=tryCatch(tolower(x),error=function(e)e)

                     if(inherits(try_error,"error"))
                       y - tolower (x)

                     return(y)
                   }

                   Tweets=sapply (Tweets, tryTolower)
                   word_list = str_split(Tweets, '\\s+') # splits the tweets by word in a list
                   words = unlist(word_list) # turns the list into vector





                   positive.matches = match(words, positivwords) ## returns matching 
                   negative.matches = match(words, negativwords)

                   positive_matches = !is.na(positive.matches) ## converts matching values to true of false
                   negative_matches = !is.na(negative.matches)

                   score = sum(positive_matches) - sum(negative_matches) # true and false are 

                   return(score)

                 }, positive_matches, negative_matches, .progress -.progress )
  return(score)
}