Impacts of Mainstream-Driven Algorithms on Recommendations for Children Across Domains: A Reproducibility Study

TL;DR

This study reproduces and extends previous research on how recommendation algorithms impact children across various domains, revealing consistent and domain-specific interaction patterns and biases, and emphasizing the importance of considering children as a distinct user group.

Contribution

It replicates and extends prior findings on child-recommender interactions across multiple datasets and domains, incorporating new bias metrics and broader analysis.

Findings

Children's consumption patterns differ from mainstream users.

Recommendation performance varies significantly for children.

Bias metrics reveal domain-specific and intrinsic differences.

Abstract

Children are often exposed to items curated by recommendation algorithms. Yet, research seldom considers children as a user group, and when it does, it is anchored on datasets where children are underrepresented, risking overlooking their interests, favoring those of the majority, i.e., mainstream users. Recently, Ungruh et al. demonstrated that children's consumption patterns and preferences differ from those of mainstream users, resulting in inconsistent recommendation algorithm performance and behavior for this user group. These findings, however, are based on two datasets with a limited child user sample. We reproduce and replicate this study on a wider range of datasets in the movie, music, and book domains, uncovering interaction patterns and aspects of child-recommender interactions consistent across domains, as well as those specific to some user samples in the data. We also extend insights from the original study with popularity bias metrics, given the interpretation of results from the original study. With this reproduction and extension, we uncover consumption patterns and differences between age groups stemming from intrinsic differences between children and others, and those unique to specific datasets or domains.