Estimating Political Ideology on Twitter via Linear Inverse Modeling

Author

G. Joy Sangeeth Raj, M Sudhakar, Chaudhari Soham, Kanjarla Vaishnavi, P Akhila

Abstract

 Online Social Networks (OSNs) have evolved into central platforms for political discourse, opinion dissemination, and media commentary. However, public news coverage and political punditry in these networks are frequently marked by partisan bias. Estimating the political leaning of social media actors presents significant challenges in terms of quantification and computational scalability. In this paper, we formulate political leaning estimation as an ill-posed linear inverse problem based on a consistency principle between tweeting and retweeting behaviors. Our proposed convex optimization formulation directly infers numerical leaning scores without requiring explicit crawling of full network topologies or graph traversal. We evaluate our method using a dataset of 119 million U.S. election-related tweets collected over seven months. Empirical results demonstrate strong alignment with conventional media bias baselines while remaining resilient to API rate limits and computational overhead.

Keywords

Political leaning; Online Social Networks; Twitter; Retweet dynamics; Linear inverse optimization; Media bias; Sentiment analysis.

Full Text:

Download Paper PDF

References

[1] M. D. Conover, J. Ratkiewicz, M. Francisco, B. Gonçalves, A. Flammini, and F. Menczer, “Political Polarization on Twitter,” Proceedings of the International AAAI Conference on Web and Social Media, vol. 5, no. 1, pp. 89–96, 2011.

[2] M. D. Conover, B. Gonçalves, A. Flammini, and F. Menczer, “Partisan Asymmetries in Online Political Activity,” EPJ Data Science, vol. 1, article 6, 2012.

[3] D. Gayo-Avello, “A Meta-Analysis of State-of-the-Art Electoral Prediction from Twitter Data,” arXiv:1206.5851, 2012.

[4] P. Barberá, “Birds of the Same Feather Tweet Together: Bayesian Ideal Point Estimation Using Twitter Data,” Political Analysis, vol. 23, no. 1, pp. 76–91, 2015.

[5] P. Barberá, J. T. Jost, J. Nagler, J. A. Tucker, and R. Bonneau, “Tweeting From Left to Right: Is Online Political Communication More Than an Echo Chamber?” Psychological Science, vol. 26, no. 10, pp. 1531–1542, 2015.

[6] F. M. F. Wong, C. W. Tan, S. Sen, and M. Chiang, “Quantifying Political Leaning from Tweets and Retweets,” Proceedings of the International AAAI Conference on Web and Social Media, vol. 7, no. 1, pp. 640–649, 2013.

[7] D. Gayo-Avello, “No, You Cannot Predict Elections with Twitter,” IEEE Internet Computing, vol. 16, no. 6, pp. 91–94, 2012.