Uncertainty in Repeated Implicit Feedback as a Measure of Reliability

TL;DR

This paper investigates the uncertainty in repeated implicit feedback in recommender systems, especially in music streaming, proposing methods to quantify and incorporate this uncertainty to improve recommendation accuracy.

Contribution

It introduces a novel Bayesian model for implicit feedback, analyzes the impact of repetition on user interest, and provides a new dataset for studying uncertainty in repeated consumption.

Findings

Incorporating uncertainty improves recommendation relevance.

Repeated consumption patterns influence user interest dynamics.

A new dataset and Bayesian model enhance understanding of implicit feedback.

Abstract

Recommender systems rely heavily on user feedback to learn effective user and item representations. Despite their widespread adoption, limited attention has been given to the uncertainty inherent in the feedback used to train these systems. Both implicit and explicit feedback are prone to noise due to the variability in human interactions, with implicit feedback being particularly challenging. In collaborative filtering, the reliability of interaction signals is critical, as these signals determine user and item similarities. Thus, deriving accurate confidence measures from implicit feedback is essential for ensuring the reliability of these signals. A common assumption in academia and industry is that repeated interactions indicate stronger user interest, increasing confidence in preference estimates. However, in domains such as music streaming, repeated consumption can shift user preferences over time due to factors like satiation and exposure. While literature on repeated consumption acknowledges these dynamics, they are often overlooked when deriving confidence scores for implicit feedback. This paper addresses this gap by focusing on music streaming, where repeated interactions are frequent and quantifiable. We analyze how repetition patterns intersect with key factors influencing user interest and develop methods to quantify the associated uncertainty. These uncertainty measures are then integrated as consistency metrics in a recommendation task. Our empirical results show that incorporating uncertainty into user preference models yields more accurate and relevant recommendations. Key contributions include a comprehensive analysis of uncertainty in repeated consumption patterns, the release of a novel dataset, and a Bayesian model for implicit listening feedback.