Non-lexical Features Encode Political Affiliation on Twitter

Rachael Tatman, Leo Stewart, Amandalynne Paullada, Emma Spiro


Abstract
Previous work on classifying Twitter users’ political alignment has mainly focused on lexical and social network features. This study provides evidence that political affiliation is also reflected in features which have been previously overlooked: 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.
Anthology ID:
W17-2909
Volume:
Proceedings of the Second Workshop on NLP and Computational Social Science
Month:
August
Year:
2017
Address:
Vancouver, Canada
Editors:
Dirk Hovy, Svitlana Volkova, David Bamman, David Jurgens, Brendan O’Connor, Oren Tsur, A. Seza Doğruöz
Venue:
NLP+CSS
SIG:
Publisher:
Association for Computational Linguistics
Note:
Pages:
63–67
Language:
URL:
https://aclanthology.org/W17-2909
DOI:
10.18653/v1/W17-2909
Bibkey:
Cite (ACL):
Rachael Tatman, Leo Stewart, Amandalynne Paullada, and Emma Spiro. 2017. Non-lexical Features Encode Political Affiliation on Twitter. In Proceedings of the Second Workshop on NLP and Computational Social Science, pages 63–67, Vancouver, Canada. Association for Computational Linguistics.
Cite (Informal):
Non-lexical Features Encode Political Affiliation on Twitter (Tatman et al., NLP+CSS 2017)
Copy Citation:
PDF:
https://aclanthology.org/W17-2909.pdf