AffectiveTweets is a WEKA package for analyzing emotion and sentiment of English written tweets.
The package implements WEKA filters for calculating state-of-the-art affective analysis features from tweets that can be fed into machine learning algorithms. Many of these features were drawn from the NRC-Canada System. It also implements methods for building affective lexicons and distant supervision methods for training affective models from unlabelled tweets.
The package was made available as the official baseline system for the WASSA-2017 Shared Task on Emotion Intensity (EmoInt) and for SemEval-2018 Task 1: Affect in Tweets.
Five participating teams used AffectiveTweets in WASSA-2017 to generate feature vectors, including the teams that eventually ranked first, second, and third. For SemEval-2018, the package was used by 15 teams.
https://affectivetweets.cms.waikato.ac.nz/
The most relevant papers on which this package is based are:
Please cite the following paper if using this package in an academic publication:
You are also welcome to cite a previous publication describing the package:
You should also cite the papers describing any of the lexicons or resources you are using with this package.
Here is the BibTex entry for the package along with the entries for the resources included in the package.
Here is the BibTex entry just for the package.
