Quantifying Political Leaning from Tweets and Retweets


  • Felix Ming Fai Wong Princeton University
  • Chee Wei Tan City University of Hong Kong
  • Soumya Sen Princeton University
  • Mung Chiang Princeton University




media, politics, elections, convex optimization


Media outlets and pundits have been quick to embrace online social networks to disseminate their own opinions. But pundits’ opinions and news coverage are often marked by a clear political bias, as widely evidenced during the fiercely contested
2012 U.S. presidential elections. Given the wide availability of such data from sites like Twitter, a natural question is whether we can quantify the political leanings of media outlets using OSN data. In this work, by drawing a correspondence between tweeting and retweeting behavior, we formulate political leaning estimation as an ill-posed linear inverse problem. The result is a simple and scalable approach that does not require explicit knowledge of the network topology. We evaluate our method with a dataset of 119 million election-related tweets collected from April to November, and use it to study the political leaning of prominent tweeters and media sources.




How to Cite

Wong, F. M. F., Tan, C. W., Sen, S., & Chiang, M. (2021). Quantifying Political Leaning from Tweets and Retweets. Proceedings of the International AAAI Conference on Web and Social Media, 7(1), 640-649. https://doi.org/10.1609/icwsm.v7i1.14422