Non-lexical Features Encode Political Affiliation on Twitter

TitleNon-lexical Features Encode Political Affiliation on Twitter
Publication TypeConference Proceedings
Year of Conference2017
AuthorsTatman, R., Stewart L., Paullada A., & Spiro E.
Conference NameWorkshop on Natural Language Processing and Computational Social Science at ACL

Previous work on classifying Twitter users’ political alignment has mainly focused on lexical and social network fea
tures. This study provides evidence that political affiliation is also reflected in features which have been previously over-looked: users’ discourse patterns (proportion of Tweets that are retweets or replies) and their rate of use of capitalization and punctuation. We find robust differences between politically left- and right-leaning communities with respect to these discourse and sub-lexical features, although they are not enough to train a high-accuracy classifier.