Week 7

Sentiment Analysis

# Load libraries
library(dplyr)

Attaching package: ‘dplyr’

The following objects are masked from ‘package:stats’:

    filter, lag

The following objects are masked from ‘package:base’:

    intersect, setdiff, setequal, union

library(tidytext)
library(readtext)

# creates dataframe with all of the text documents
# change directory so that it refers to the location of the 72 text documents on your computer
transcripts<-readtext("~/Documents/School/ACG 6176- Evaluation of Financial Reports, Business Analysis & Valuation/Week 7/Transcripts")
View(transcripts)

# Transform the text data to tidy text data
tidy_transcripts <- transcripts %>%
  group_by(doc_id) %>%
  unnest_tokens(word, text) %>%
  ungroup()

# Use count to find out how many times each word is used
wordcount_per_document<-tidy_transcripts %>%group_by(doc_id)%>% count(word, sort = TRUE)%>%mutate(totalwordcount=sum(n))
wordcount_per_document2<-wordcount_per_document[,c("doc_id", "totalwordcount")]
wordcount_per_document3<-wordcount_per_document2 %>% distinct

# Implement sentiment analysis with the Loughran and McDonald positive and negative (financial) word list
tidy_sentiment <- tidy_transcripts %>%
  inner_join(get_sentiments("loughran")) %>% filter(sentiment == "positive" | sentiment=="negative")

Joining, by = "word"

# Find how many positive/negative words each document has
sentiment_counts <- tidy_sentiment %>%
  count(doc_id, sentiment)
sentiment_counts2 <- merge(wordcount_per_document3,sentiment_counts,by="doc_id")
positive <- sentiment_counts2 %>% filter(sentiment == "positive") %>% mutate(positive_word_count=n)
negative <- sentiment_counts2 %>% filter(sentiment == "negative") %>% mutate(negative_word_count=n)
sentiment_counts3 <- merge(positive,negative,by=c("doc_id", "totalwordcount"))

tone <- sentiment_counts3 %>% mutate(tone=((positive_word_count-negative_word_count)/totalwordcount)*100)
View(tone)

Add a new chunk by clicking the Insert Chunk button on the toolbar or by pressing Cmd+Option+I.

When you save the notebook, an HTML file containing the code and output will be saved alongside it (click the Preview button or press Cmd+Shift+K to preview the HTML file).

The preview shows you a rendered HTML copy of the contents of the editor. Consequently, unlike Knit, Preview does not run any R code chunks. Instead, the output of the chunk when it was last run in the editor is displayed.