Positive, Negative and Neutral: Modeling Implicit Feedback in Session-based News Recommendation

TL;DR

This paper introduces a comprehensive framework for session-based news recommendation that models implicit user feedback, including positive, negative, and neutral signals, leading to more accurate and diverse recommendations.

Contribution

It is the first to incorporate implicit feedback signals like skipping and session timing into session-based news recommendation models.

Findings

Outperforms state-of-the-art methods in accuracy

Provides more diverse and unexpected recommendations

Effectively models user preferences using implicit feedback

Abstract

News recommendation for anonymous readers is a useful but challenging task for many news portals, where interactions between readers and articles are limited within a temporary login session. Previous works tend to formulate session-based recommendation as a next item prediction task, while they neglect the implicit feedback from user behaviors, which indicates what users really like or dislike. Hence, we propose a comprehensive framework to model user behaviors through positive feedback (i.e., the articles they spend more time on) and negative feedback (i.e., the articles they choose to skip without clicking in). Moreover, the framework implicitly models the user using their session start time, and the article using its initial publishing time, in what we call "neutral feedback". Empirical evaluation on three real-world news datasets shows the framework's promising performance of more accurate, diverse and even unexpectedness recommendations than other state-of-the-art session-based recommendation approaches.