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

arXiv: https://arxiv.org/abs/1711.10251 · HTML: https://mlsanity.com/paper/1711.10251/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Nov 2017.

## Built on by (most cited first, 5 of 5)

- [Fine-Grained Prediction of Political Leaning on Social Media with Unsupervised Deep Learning](https://mlsanity.com/paper/2202.12382/) (2022)
- [Learning Ideological Embeddings from Information Cascades](https://mlsanity.com/paper/2109.13589/) (2021)
- [Random Walks with Erasure: Diversifying Personalized Recommendations on Social and Information Networks](https://mlsanity.com/paper/2102.09635/) (2021)
- [Improving Stance Detection by Leveraging Measurement Knowledge from Social Sciences: A Case Study of Dutch Political Tweets and Traditional Gender Role Division](https://mlsanity.com/paper/2212.06543/) (2022)
- [Iterative Topic Taxonomy Induction with LLMs: A Case Study of Electoral Advertising](https://mlsanity.com/paper/2510.15125/) (2025)

## Abstract (arXiv)

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.