FEBR: Expert-Based Recommendation Framework for beneficial and personalized content
This addresses the problem of ensuring high-quality and reliable content recommendations for users on online platforms, though it is incremental as it builds on existing apprenticeship learning techniques.
The paper tackles the challenge of evaluating content quality and reliability in recommender systems by proposing FEBR, an apprenticeship learning framework that uses expert trajectories to recover a utility function and learn an optimal policy for recommendations. Results show a significant gain in content quality while maintaining similar watch time compared to baseline methods.
So far, most research on recommender systems focused on maintaining long-term user engagement and satisfaction, by promoting relevant and personalized content. However, it is still very challenging to evaluate the quality and the reliability of this content. In this paper, we propose FEBR (Expert-Based Recommendation Framework), an apprenticeship learning framework to assess the quality of the recommended content on online platforms. The framework exploits the demonstrated trajectories of an expert (assumed to be reliable) in a recommendation evaluation environment, to recover an unknown utility function. This function is used to learn an optimal policy describing the expert's behavior, which is then used in the framework to provide high-quality and personalized recommendations. We evaluate the performance of our solution through a user interest simulation environment (using RecSim). We simulate interactions under the aforementioned expert policy for videos recommendation, and compare its efficiency with standard recommendation methods. The results show that our approach provides a significant gain in terms of content quality, evaluated by experts and watched by users, while maintaining almost the same watch time as the baseline approaches.