Analyse Sentiment of English Sentences

Analyses sentiment of a sentence in English and assigns score to it. It can classify sentences to the following categories of sentiments:- Positive, Negative, very Positive, very negative, Neutral. For a vector of sentences, it counts the number of sentences in each category of sentiment.In calculating the score, negation and various degrees of adjectives are taken into consideration. It deals only with English sentences.


A package in R to analyse sentiment of English sentences


This package contains three functions that allow R users to analyse sentiment (Positive, Negative, Very Positive, Very Negative, Neutral, Sarcasm) of a text. This package is currently supported in English only.

Current CRAN release is 2.1.3. To install the most updated version of this package from CRAN, run the following code.

install.packages("RSentiment")

calculate_score()

This function loads text and calculates score of each sentence of the text fed on basis of following conditions.

  • Parts of Speech tagging of each word of the sentence
  • Identifying various conditions of occurrences and presence of Verb, Adverb, Adjective, Noun etc in each sentence
  • Accordingly, marking the presence of words of positive and negative sentiment and order of their occurence
  • Considering negation
  • Checking for sarcasm on basis of presence of punctuation(currently)
  • Checking presence of emoticons in the text

This method can provide result in the following range.

  • 0 indicates neutral sentiment.
  • Positive value indicates positive sentiment.
  • Negative value indicates negative sentiment.
  • 99 indicates sarcasm.

calculate_sentiment()

This function loads text and calculates sentiment of each sentence. This function uses the score predicted by calculate_score method to classify the sentences. It classifies sentences into 6 categories:

  • Positive
  • Negative
  • Very Positive
  • Very Negative
  • Sarcasm
  • Neutral

calculate_total_presence_sentiment()

This function loads text and calculates number of sentences under each category of

  • Positive
  • Negative
  • Very Positive
  • Very Negative
  • Neutral
  • Sarcasm.

News

Reference manual

It appears you don't have a PDF plugin for this browser. You can click here to download the reference manual.

install.packages("RSentiment")

2.2.1 by Subhasree Bose, 6 months ago


Browse source code at https://github.com/cran/RSentiment


Authors: Subhasree Bose <[email protected]> with contributons from Saptarsi Goswami.


Documentation:   PDF Manual  


GPL-2 license


Imports plyr, stringr, openNLP, NLP

Suggests knitr, rmarkdown, testthat


See at CRAN