Institute Homepage DE Sign In
Social Foundations of Computation Members Publications

Algorithmic Collective Action in Recommender Systems: Promoting Songs by Reordering Playlists

Small collectives can hugely amplify a target song relative to its frequency in the training data.

This work examines how small collectives can amplify recommendations for a targeted song in transformer-based recommender systems with minimal platform performance impact, revealing non-adversarial yet effective strategies that raise broader questions about incentives and social dynamics [File Icon].

Members

Social Foundations of Computation
Joachim Baumann
Algorithms and Society
Celestine Mendler-Dünner
PI Alumna, Hector Endowed Fellow

Publications

Social Foundations of Computation Algorithms and Society Conference Paper Algorithmic Collective Action in Recommender Systems: Promoting Songs by Reordering Playlists Baumann, J., Mendler-Dünner, C. Advances in Neural Information Processing Systems 37 (NeurIPS 2024) , (Editors: A. Globerson and L. Mackey and D. Belgrave and A. Fan and U. Paquet and J. Tomczak and C. Zhang), Curran Associates, Inc., Annual Conference on Neural Information Processing Systems (NeurIPS), December 2024 (Published) arXiv URL BibTeX