D-RDW: Diversity-Driven Random Walks for News Recommender Systems

TL;DR

D-RDW is a lightweight, transparent re-ranking algorithm that enhances diversity in news recommendations by integrating societal norms, outperforming neural models in diversity metrics and computational efficiency.

Contribution

This paper presents D-RDW, a novel diversity-driven random walk algorithm that allows customizable societal norm incorporation into news recommendation re-ranking.

Findings

D-RDW improves diversity metrics related to sentiment and political mentions.

D-RDW outperforms neural models in diversity and efficiency.

D-RDW is computationally more efficient than existing methods.

Abstract

This paper introduces Diversity-Driven RandomWalks (D-RDW), a lightweight algorithm and re-ranking technique that generates diverse news recommendations. D-RDW is a societal recommender, which combines the diversification capabilities of the traditional random walk algorithms with customizable target distributions of news article properties. In doing so, our model provides a transparent approach for editors to incorporate norms and values into the recommendation process. D-RDW shows enhanced performance across key diversity metrics that consider the articles' sentiment and political party mentions when compared to state-of-the-art neural models. Furthermore, D-RDW proves to be more computationally efficient than existing approaches.