Balanced News Using Constrained Bandit-based Personalization

TL;DR

This paper introduces a news search engine prototype that uses constrained bandit algorithms to present balanced liberal and conservative articles, aiming to reduce polarization and filter bubble effects.

Contribution

It applies constrained bandit optimization to personalize news feeds with user-defined balance constraints, a novel approach in news personalization.

Findings

Effective balancing of news viewpoints demonstrated

Reduced polarization compared to traditional feeds

Flexible user constraints enable customizable content balance

Abstract

We present a prototype for a news search engine that presents balanced viewpoints across liberal and conservative articles with the goal of de-polarizing 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.