HW_10

##Get lexicon

df_afin <- get_sentiments("afinn")
df_bing <- get_sentiments("bing")
df_nrc <- get_sentiments("nrc")

##Get Data

text_data <- gutenberg_download(1963) 

## Determining mirror for Project Gutenberg from https://www.gutenberg.org/robot/harvest

## Using mirror http://aleph.gutenberg.org

##Analysis

tidy_data_bing <- text_data %>%
  unnest_tokens(word, text) %>%
  inner_join(df_bing)

## Joining with `by = join_by(word)`

tidy_data_bing %>%
  count(sentiment) %>%
  ggplot(aes(x = sentiment, y = n, fill = sentiment)) +
  geom_bar(stat = "identity") +
  ggtitle("Sentiment distribution using Bing lexicon")

text_vector <- paste(text_data$text, collapse = " ") 

nrc_sentiment <- get_nrc_sentiment(text_vector)

nrc_sentiment %>%
  colSums() %>%
  enframe(name = "sentiment", value = "count") %>%
  ggplot(aes(x = sentiment, y = count, fill = sentiment)) +
  geom_bar(stat = "identity") +
  ggtitle("Sentiment distribution using NRC lexicon")