FEBR: Expert-Based Recommendation Framework for beneficial and personalized content

TL;DR

FEBR is a framework that uses expert demonstrations to evaluate and improve the quality of personalized content recommendations, ensuring higher content quality without sacrificing user engagement.

Contribution

The paper introduces FEBR, a novel apprenticeship learning framework that assesses content quality and enhances recommendation policies using expert trajectories.

Findings

Significant improvement in content quality as rated by experts.

Maintains similar user watch time compared to baseline methods.

Effective in simulated video recommendation environments.

Abstract

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.