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.
@article{arxiv.1806.09202,
title = {Balanced News Using Constrained Bandit-based Personalization},
author = {Sayash Kapoor and Vijay Keswani and Nisheeth K. Vishnoi and L. Elisa Celis},
journal= {arXiv preprint arXiv:1806.09202},
year = {2018}
}