A News Recommender System Considering Temporal Dynamics and Diversity

TL;DR

This paper presents a news recommender system that dynamically adapts to changing reader preferences over time and balances accuracy with diversity to enhance user engagement and societal fairness.

Contribution

It introduces a novel model that captures temporal dynamics in user preferences and incorporates diversity, addressing limitations of existing systems that focus mainly on accuracy.

Findings

The system effectively models short-term and long-term preferences.

It improves recommendation diversity without sacrificing accuracy.

The approach works well for anonymous and short-term users.

Abstract

In a news recommender system, a reader's preferences change over time. Some preferences drift quite abruptly (short-term preferences), while others change over a longer period of time (long-term preferences). Although the existing news recommender systems consider the reader's full history, they often ignore the dynamics in the reader's behavior. Thus, they cannot meet the demand of the news readers for their time-varying preferences. In addition, the state-of-the-art news recommendation models are often focused on providing accurate predictions, which can work well in traditional recommendation scenarios. However, in a news recommender system, diversity is essential, not only to keep news readers engaged, but also to play a key role in a democratic society. In this PhD dissertation, our goal is to build a news recommender system to address these two challenges. Our system should be able to: (i) accommodate the dynamics in reader behavior; and (ii) consider both accuracy and diversity in the design of the recommendation model. Our news recommender system can also work for unprofiled, anonymous and short-term readers, by leveraging the rich side information of the news items and by including the implicit feedback in our model. We evaluate our model with multiple evaluation measures (both accuracy and diversity-oriented metrics) to demonstrate the effectiveness of our methods.