Joint Non-negative Matrix Factorization for Learning Ideological Leaning on Twitter

TL;DR

This paper introduces a joint non-negative matrix factorization method to learn and analyze the ideological spectrum of Twitter users and media sources, aiming to mitigate filter bubbles and polarization.

Contribution

It presents a novel constrained NMF model that jointly incorporates social network and content data to accurately infer ideological positions on Twitter.

Findings

Achieves over 90% purity in separating users by ideology

Estimates media source ideology scores with 0.9 correlation to ground truth

Demonstrates practical applications in reducing filter bubbles

Abstract

People are shifting from traditional news sources to online news at an incredibly fast rate. However, the technology behind online news consumption promotes content that confirms the users' existing point of view. This phenomenon has led to polarization of opinions and intolerance towards opposing views. Thus, a key problem is to model information filter bubbles on social media and design methods to eliminate them. In this paper, we use a machine-learning approach to learn a liberal-conservative ideology space on Twitter, and show how we can use the learned latent space to tackle the filter bubble problem. We model the problem of learning the liberal-conservative ideology space of social media users and media sources as a constrained non-negative matrix-factorization problem. Our model incorporates the social-network structure and content-consumption information in a joint factorization problem with shared latent factors. We validate our model and solution on a real-world Twitter dataset consisting of controversial topics, and show that we are able to separate users by ideology with over 90% purity. When applied to media sources, our approach estimates ideology scores that are highly correlated (Pearson correlation 0.9) with ground-truth ideology scores. Finally, we demonstrate the utility of our model in real-world scenarios, by illustrating how the learned ideology latent space can be used to develop exploratory and interactive interfaces that can help users in diffusing their information filter bubble.