Tidytext R package

The Shiny application Sentiment analysis dashboard using tidytext R text mining shows how to work with text using tidytext package developed by (Silge and Robinson, 2016). The theory and examples are prestented in the book Text mining with R. Authors arguee, that using tidy data principles can make many text mining tasks easier, more effective, and consistent with tools already in wide use.

This technique applied for the sentiment analysis treat text as data frames of individual words allows to manipulate, summarize, and visualize the characteristics of text easily. The analysis is based on the two lexicons containing sentimental words.

BING lexicon: negative positive

NRC lexicon: trust fear negative sadness anger surprise positive disgust joy anticipation

Tabs in app

• TEXT editor - input text, choose the lexicon, see how many words is in your text (excluding stop-words)
• Is YOUR text sentimental - analysie the text comparing with sentimental words in from the lexicon
• Grammar and comparison - analysie relationships between words: 2-grams and correlations

Informations about this technique

• https://cran.r-project.org/web/packages/tidytext/vignettes/tidytext.html
• https://www.r-bloggers.com/tidy-text-mining-with-r/