Dictionary-Based Analysis

website: https://www.chrisbail.net
github: https://github.com/cbail
Twitter: https://www.twitter.com/chris_bail

data("stop_words")
trump_tweet_top_words<-
   tidy_trump_tweets %>%
      anti_join(stop_words) %>%
        count(word) %>%
        arrange(desc(n))
trump_tweet_top_words<-
  trump_tweet_top_words[-grep("https|t.co|amp|rt",
                              trump_tweet_top_words$word),]
top_20<-trump_tweet_top_words[1:20,]

library(ggplot2)
ggplot(top_20, aes(x=word, y=n, fill=word))+
  geom_bar(stat="identity")+
  theme_minimal()+
  theme(axis.text.x = element_text(angle = 90, hjust = 1))+
  ylab("Number of Times Word Appears in Trump's Tweets")+
  xlab("")+
  guides(fill=FALSE)

tidy_trump_tfidf<- trumptweets %>%
    select(created_at,text) %>%
      unnest_tokens("word", text) %>%
        anti_join(stop_words) %>%
           count(word, created_at) %>%
              bind_tf_idf(word, created_at, n)

top_tfidf<-tidy_trump_tfidf %>%
  arrange(desc(tf_idf))

top_tfidf$word[1]

[1] "standforouranthem"

economic_dictionary<-c("economy","unemployment","trade","tariffs")

library(stringr)
economic_tweets<-trumptweets[str_detect(trumptweets$text, economic_dictionary),]
head(economic_tweets$text, 2)

[1] "Great talk with my friend President Mauricio Macri of Argentina this week. He is doing such a good job for Argentina. I support his vision for transforming his country’s economy and unleashing its potential!"                                                         
[2] "The Washington Post and CNN have typically written false stories about our trade negotiations with China. Nothing has happened with ZTE except as it pertains to the larger trade deal. Our country has been losing hundreds of billions of dollars a year with China..."

head(get_sentiments("afinn"))

# A tibble: 6 x 2
  word       value
  <chr>      <dbl>
1 abandon       -2
2 abandoned     -2
3 abandons      -2
4 abducted      -2
5 abduction     -2
6 abductions    -2

trump_tweet_sentiment <- tidy_trump_tweets %>%
  inner_join(get_sentiments("bing")) %>%
    count(created_at, sentiment) 

head(trump_tweet_sentiment)

# A tibble: 6 x 3
  created_at          sentiment     n
  <dttm>              <chr>     <int>
1 2017-02-05 22:49:42 positive      2
2 2017-02-06 03:36:54 positive      4
3 2017-02-06 12:01:53 negative      3
4 2017-02-06 12:01:53 positive      1
5 2017-02-06 12:07:55 negative      2
6 2017-02-06 16:32:24 negative      3

tidy_trump_tweets$date<-as.Date(tidy_trump_tweets$created_at, 
                                          format="%Y-%m-%d %x")

trump_sentiment_plot <-
  tidy_trump_tweets %>%
    inner_join(get_sentiments("bing")) %>% 
      filter(sentiment=="negative") %>%
          count(date, sentiment)

library(ggplot2)

ggplot(trump_sentiment_plot, aes(x=date, y=n))+
  geom_line(color="red")+
    theme_minimal()+
      ylab("Frequency of Negative Words in Trump's Tweets")+
        xlab("Date")

#plot
ggplot(approval_plot, aes(x=date, y=approval))+
  geom_line(group=1)+
    theme_minimal()+
      ylab("% of American Adults who Approve of Trump")+
        xlab("Date")