Impacts of Mainstream-Driven Algorithms on Recommendations for Children Across Domains: A Reproducibility Study
Robin Ungruh, Alejandro Bellogín, Dominik Kowald, and Maria Soledad Pera. 2025. “Impacts of Mainstream-Driven Algorithms on Recommendations for Children Across Domains: A Reproducibility Study”. In Proceedings of the 19th ACM Conference on Recommender Systems (RecSys 2025), pp. 783-791. ACM. DOI:10.1145/3705328.3748160.
Abstract
Recommender systems research seldom considers children as a user group, and when it does, it is anchored on datasets where children are under-represented, risking overlooking their interests and favouring those of the majority (“mainstream” users). We reproduce and replicate an earlier study on a wider range of datasets in the movie, music, and book domains, thereby uncovering interaction patterns and aspects of child-recommender interactions that are consistent across domains as well as those specific to particular user samples and domains. We extend the original study’s insights with popularity bias metrics and show that differences between age groups stem from both intrinsic differences between children and other users and domain-specific dynamics.