Sentiment Analysis

Click here to return to projects page

Sentiment analysis provides a way to understand the attitudes and opinions expressed in texts. Each word can be assigned an emotion or sentiment such as positive or negative or other categories such as happy, joy, fear, etc. The sentiment of each word can be best identified for a particular problem. For example, when studying positive and negative affects, one can ask people to identify whether a word shows positive or negative meanings. This website provides several lexicons based on research to enable to see the result of a sentiment analysis based on several methodologies.

The repository for this project can be found here

AFINN is a list of English words that are rated and give a value between -5 (negative) and +5 (positive). Afinn is the simplest yet popular lexicons used for sentiment analysis developed by Finn Årup Nielsen. It contains 3300+ words with a polarity score associated with each word. The implementation here uses Afinn-165


  • > 0 - positive sentiment
  • 0 - neutral sentiment
  • < 0 - negative sentiment

Finn Årup Nielsen, "A new ANEW: evaluation of a word list for sentiment analysis in microblogs", Proceedings of the ESWC2011 Workshop on 'Making Sense of Microposts': Big things come in small packages. Volume 718 in CEUR Workshop Proceedings: 93-98. 2011 May. Matthew Rowe, Milan Stankovic, Aba-Sah Dadzie, Mariann Hardey (editors)

Please refer here for more information

VADER (Valence Aware Dictionary and sEntiment Reasoner) is a lexicon and rule-based sentiment analysis tool that is specifically attuned to sentiments expressed in social media.

The Compound score is a metric that calculates the sum of all the lexicon ratings which have been

  • -1(most extreme negative) and +1 (most extreme positive).
  • positive sentiment : (compound score >= 0.05)
  • neutral sentiment : (compound score > -0.05) and (compound score < 0.05)
  • negative sentiment : (compound score <= -0.05)

Hutto, C.J. & Gilbert, E.E. (2014). VADER: A Parsimonious Rule-based Model for Sentiment Analysis of Social Media Text. Eighth International Conference on Weblogs and Social Media (ICWSM-14). Ann Arbor, MI, June 2014.

Please refer here for more information

The NRC Emotion Lexicon is a list of English words and their associations with eight basic emotions (anger, fear, anticipation, trust, surprise, sadness, joy, and disgust) and two sentiments (negative and positive). The annotations were manually done by crowd-sourcing.

Lexicon source is (C) 2016 National Research Council Canada (NRC) and this package is for research purposes only. Source: As per the terms of use of the NRC Emotion Lexicon, if you use the lexicon or any derivative from it, cite this paper: Crowdsourcing a Word-Emotion Association Lexicon, Saif Mohammad and Peter Turney, Computational Intelligence, 29 (3), 436-465, 2013.

Please refer here for more information

Lexicon home page here

The NRC Valence, Arousal, and Dominance (VAD) Lexicon includes a list of more than 20,000 English words and their valence, arousal, and dominance scores. For a given word and a dimension (V/A/D), the scores range from 0 (lowest V/A/D) to 1 (highest V/A/D). The lexicon with its fine-grained real-valued scores was created by manual annotation using Best--Worst Scaling. The lexicon is markedly larger than any of the existing VAD lexicons

Words play a central role in language and thought. Several influential factor analysis studies have shown that the primary dimensions of word meaning are valence, arousal, and dominance (VAD) (Osgood et al., 1957; Russell, 1980, 2003).

  • valence is the positive--negative or pleasure--displeasure dimension;
  • arousal is the excited--calm or active--passive dimension; and
  • dominance is the powerful--weak or 'have full control'--'have no control' dimension.

Please refer here for more information

Lexicon home page here

General purpose English sentiment lexicon that categorizes words in a binary fashion, either positive or negative

Minqing Hu and Bing Liu, ``Mining and summarizing customer reviews.'', Proceedings of the ACM SIGKDD International Conference on Knowledge Discovery & Data Mining (KDD-2004), Seattle, Washington, USA, Aug 22-25, 2004.

Please refer here for more information

English sentiment lexicon created for use with financial documents.

The sentiment categories are: negative, positive, uncertainty, litigious, strong modal, weak modal, and constraining.

This sentiment dictionary, is modified to only categorize each word into its sentiment based on the master dictionary provided.

Please refer here for more information

It is possible to copy and paste whole paragraphs


Verdict will appear here

Examples that could be used

  • Good people sometimes have bad days
  • We are kind to good people
  • I'd really truly love going out in this weather!
  • I do not dislike cabin cruisers
  • I love my mobile but would not recommend it to any of my colleagues.