On Popularity Bias of Multimodal-aware Recommender Systems: a Modalities-driven Analysis

TL;DR

This paper investigates how multimodal content in recommender systems can amplify popularity bias, analyzing the separate effects of visual and textual modalities on recommendation diversity and niche item retrieval.

Contribution

It provides one of the first analyses of modality-specific impacts on popularity bias in multimodal-aware recommender systems, highlighting the need for more rigorous evaluation.

Findings

Single modalities can increase popularity bias.

Multimodal systems may reduce diversity of recommendations.

Visual and textual modalities differently influence bias and diversity.

Abstract

Multimodal-aware recommender systems (MRSs) exploit multimodal content (e.g., product images or descriptions) as items' side information to improve recommendation accuracy. While most of such methods rely on factorization models (e.g., MFBPR) as base architecture, it has been shown that MFBPR may be affected by popularity bias, meaning that it inherently tends to boost the recommendation of popular (i.e., short-head) items at the detriment of niche (i.e., long-tail) items from the catalog. Motivated by this assumption, in this work, we provide one of the first analyses on how multimodality in recommendation could further amplify popularity bias. Concretely, we evaluate the performance of four state-of-the-art MRSs algorithms (i.e., VBPR, MMGCN, GRCN, LATTICE) on three datasets from Amazon by assessing, along with recommendation accuracy metrics, performance measures accounting for the diversity of recommended items and the portion of retrieved niche items. To better investigate this aspect, we decide to study the separate influence of each modality (i.e., visual and textual) on popularity bias in different evaluation dimensions. Results, which demonstrate how the single modality may augment the negative effect of popularity bias, shed light on the importance to provide a more rigorous analysis of the performance of such models.