library(jsonlite)
library(dplyr)
library(sentimentr)
library(tidyverse)
library(readr)
library(tm)
library(syuzhet)
library(tidytext)
library(ggplot2)
library(quanteda)

Loading in data

tweets <- readRDS("~/networks-blog/boliviatweetsfile")
tweets <- iconv(tweets$text, to = "ASCII", sub = " ")
tweets <- gsub("(RT|via)((?:\\b\\W*@\\w+)+)", "", tweets)  # Remove the "RT" (retweet) and usernames 
tweets = gsub("http.+ |http.+$", " ", tweets)  # Remove html links
tweets = gsub("http[[:alnum:]]*", "", tweets)
tweets = gsub("[[:punct:]]", " ", tweets)  # Remove punctuation
tweets = gsub("[ |\t]{2,}", " ", tweets)  # Remove tabs
tweets = gsub("^ ", "", tweets)  # Leading blanks
tweets = gsub(" $", "", tweets)  # Lagging blanks
tweets = gsub(" +", " ", tweets) # General spaces

tweets = tolower(tweets)
tweets = unique(tweets)
corpus <- Corpus(VectorSource(tweets))
corpus <- tm_map(corpus, removeWords, stopwords("english"))  
corpus <- tm_map(corpus, removeNumbers)

corpus <- tm_map(corpus, stemDocument)
corpus = tm_map(corpus, removeWords, c("amp", "will", "get", "can", "like", "say", "know"))

Sentiment Analysis

# Sentiment Analysis
testdata_text_sent<- get_nrc_sentiment((as.character(corpus)))

#calculating total score for each sentiment
testdata_text_sent_score<-data.frame(colSums(testdata_text_sent[,]))

names(testdata_text_sent_score)<-"Score"
testdata_text_sent_score<-cbind("sentiment"=rownames(testdata_text_sent_score),testdata_text_sent_score)
rownames(testdata_text_sent_score)<-NULL


#plotting the sentiments with scores
ggplot(data=testdata_text_sent_score,aes(x=sentiment,y=Score))+geom_bar(aes(fill=sentiment),stat = "identity")+
  theme(legend.position="none")+
  xlab("Sentiments")+ylab("scores")+ggtitle("Sentiments of Twitter Users ")

library(quanteda)
library(quanteda.sentiment)
twtDfm_nrc <- dfm(tokens(as.character(corpus), remove_punct = TRUE),
                              tolower = TRUE) %>%
                          dfm_lookup(data_dictionary_NRC)
df_nrc <- convert(twtDfm_nrc, to = "data.frame")
df_nrc$polarity <- (df_nrc$positive - df_nrc$negative)/(df_nrc$positive + df_nrc$negative)
df_nrc$polarity[which((df_nrc$positive + df_nrc$negative) == 0)] <- 0


twtDfm_lsd2015 <- dfm(tokens(as.character(corpus), remove_punct = TRUE),
                              tolower = TRUE) %>%
                          dfm_lookup(data_dictionary_LSD2015)

df_lsd2015 <- convert(twtDfm_lsd2015, to = "data.frame")
df_lsd2015$polarity <- (df_lsd2015$positive - df_lsd2015$negative)/(df_lsd2015$positive + df_lsd2015$negative)
df_lsd2015$polarity[which((df_lsd2015$positive + df_lsd2015$negative) == 0)] <- 0


twtDfm_geninq <- dfm(tokens(as.character(corpus), remove_punct = TRUE),
                             tolower = TRUE) %>%
                    dfm_lookup(data_dictionary_geninqposneg)
df_geninq <- convert(twtDfm_geninq, to = "data.frame")
df_geninq$polarity <- (df_geninq$positive - df_geninq$negative)/(df_geninq$positive + df_geninq$negative)
df_geninq$polarity[which((df_geninq$positive + df_geninq$negative) == 0)] <- 0

colnames(df_nrc) <- paste("nrc", colnames(df_nrc), sep = "_")
colnames(df_lsd2015) <- paste("lsd2015", colnames(df_lsd2015), sep = "_")
colnames(df_geninq) <- paste("geninq", colnames(df_geninq), sep = "_")

# now let's compare our estimates
sent_df <- merge(df_nrc, df_lsd2015, by.x = "nrc_doc_id", by.y = "lsd2015_doc_id")
sent_df <- merge(sent_df, df_geninq, by.x = "nrc_doc_id", by.y = "geninq_doc_id")

cor(sent_df$nrc_polarity, sent_df$lsd2015_polarity)

[1] -1

cor(sent_df$nrc_polarity, sent_df$geninq_polarity)

[1] 1

cor(sent_df$lsd2015_polarity, sent_df$geninq_polarity)

[1] -1

library(wordcloud)
library(reshape2)

token = data.frame(text=tweets, stringsAsFactors = FALSE) %>% 
      unnest_tokens(word, text)

token %>%
  inner_join(get_sentiments("bing")) %>%
  count(word, sentiment, sort = TRUE) %>%
  acast(word ~ sentiment, value.var = "n", fill = 0) %>%
  comparison.cloud(colors = c("red", "blue"),
                   max.words = 100)

bing_word_counts <- token %>%
  inner_join(get_sentiments("bing")) %>%
  count(word, sentiment, sort = TRUE) %>%
  ungroup()

bing_word_counts %>%
  group_by(sentiment) %>%
  slice_max(n, n = 10) %>% 
  ungroup() %>%
  mutate(word = reorder(word, n)) %>%
  ggplot(aes(n, word, fill = sentiment)) +
  geom_col(show.legend = FALSE) +
  facet_wrap(~sentiment, scales = "free_y") +
  labs(x = "Contribution to sentiment",
       y = NULL)

Blog 5

Sentiment Analysis