Accessing the NRC Emotion and Sentiment Lexicons


Since February 16, 2017 the following are no longer available for direct download at this website. They are still available free of charge for research purposes. They are also available for commercial applications via a perpetual commercial license for a nominal one-time fee.

Simply email:

Pierre Charron (Client Relationship Leader at NRC): Pierre.Charron@nrc-cnrc.gc.ca,
and cc
Saif M. Mohammad (Senior Research Officer at NRC): Saif.Mohammad@nrc-cnrc.gc.ca.

and include:

- your name and affiliation
- the name of the resource you are interested in
- what you intend to use it for
- whether you intend to use it only for research and will not include it in any commercial product OR you would like a commercial license

The Sentiment and Emotion Lexicons you can obtain by emailing include:

NRC Word-Emotion Association Lexicon aka NRC Emotion Lexicon aka EmoLex: association of words with eight emotions (anger, fear, anticipation, trust, surprise, sadness, joy, and disgust) and two sentiments (negative and positive) manually annotated on Amazon's Mechanical Turk. Available in 40 different languages.
Version: 0.92
Number of terms: 14,182 unigrams (words), ~25,000 word senses
Association scores: binary (associated or not)

NRC Hashtag Emotion Lexicon: association of words with eight emotions (anger, fear, anticipation, trust, surprise, sadness, joy, and disgust) generated automatically from tweets with emotion-word hashtags such as #happy and #anger.
Version: 0.2
Number of terms: 16,862 unigrams (words)
Association scores: real-valued

NRC Hashtag Sentiment Lexicon: association of words with positive (negative) sentiment generated automatically from tweets with sentiment-word hashtags such as #amazing and #terrible.
Version: 1.0
Number of terms: 54,129 unigrams, 316,531 bigrams, 308,808 pairs
Association scores: real-valued

NRC Hashtag Affirmative Context Sentiment Lexicon and NRC Hashtag Negated Context Sentiment Lexicon: association of words with positive (negative) sentiment in affirmative or negated contexts generated automatically from tweets with sentiment-word hashtags such as #amazing and #terrible.
Version: 1.0
Number of terms: Affirmative contexts: 36,357 unigrams, 159,479 bigrams; Negated contexts: 7,592 unigrams, 23,875 bigrams
Association scores: real-valued

NRC Emoticon Lexicon (a.k.a. Sentiment140 Lexicon): association of words with positive (negative) sentiment generated automatically from tweets with emoticons such as :) and :(.
Version: 1.0
Number of terms: 62,468 unigrams, 677,698 bigrams, 480,010 pairs
Association scores: real-valued

NRC Emoticon Affirmative Context Lexicon and NRC Emoticon Negated Context Lexicon: association of words with positive (negative) sentiment in affirmative or negated contexts generated automatically from tweets with emoticons such as :) and :(.
Version: 1.0
Number of terms: Affirmative contexts: 45,255 unigrams, 240,076 bigrams; Negated contexts: 9,891 unigrams, 34,093 bigrams
Association scores: real-valued

NRC Word-Colour Association Lexicon: association of words with colours manually annotated on Amazon's Mechanical Turk.
Version: 0.92
Number of terms: 14,182 unigrams (words), ~25,000 word senses
Association scores: binary (associated or not)