Balanced News Using Constrained Bandit-based Personalization

Balanced News Using Constrained Bandit-based Personalization

Sayash Kapoor, Vijay Keswani, Nisheeth K. Vishnoi, L. Elisa Celis

Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence

We present a prototype for a news search engine that presents balanced viewpoints across liberal and conservative articles with the goal of depolarizing content and allowing users to escape their filter bubble. The balancing is done according to flexible user-defined constraints, and leverages recent advances in constrained bandit optimization. We showcase our balanced news feed by displaying it side-by-side with the news feed produced by a traditional (polarized) feed.
Keywords:
Machine Learning: Online Learning
Multidisciplinary Topics and Applications: AI and Social Sciences
Multidisciplinary Topics and Applications: Personalization and User Modeling
Multidisciplinary Topics and Applications: Real-Time Systems