Positive, Negative and Neutral: Modeling Implicit Feedback in Session-based News Recommendation
This work addresses the problem of improving news recommendations for anonymous readers in temporary sessions, offering an incremental enhancement by incorporating implicit feedback into existing session-based frameworks.
The paper tackles session-based news recommendation by modeling implicit feedback from user behaviors, including positive, negative, and neutral signals, resulting in more accurate, diverse, and unexpected recommendations compared to state-of-the-art methods on three real-world datasets.
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.