Harm Mitigation in Recommender Systems under User Preference Dynamics
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866910487339335680 |
|---|---|
| author | Chee, Jerry Kalyanaraman, Shankar Ernala, Sindhu Kiranmai Weinsberg, Udi Dean, Sarah Ioannidis, Stratis |
| author_facet | Chee, Jerry Kalyanaraman, Shankar Ernala, Sindhu Kiranmai Weinsberg, Udi Dean, Sarah Ioannidis, Stratis |
| contents | We consider a recommender system that takes into account the interplay between recommendations, the evolution of user interests, and harmful content. We model the impact of recommendations on user behavior, particularly the tendency to consume harmful content. We seek recommendation policies that establish a tradeoff between maximizing click-through rate (CTR) and mitigating harm. We establish conditions under which the user profile dynamics have a stationary point, and propose algorithms for finding an optimal recommendation policy at stationarity. We experiment on a semi-synthetic movie recommendation setting initialized with real data and observe that our policies outperform baselines at simultaneously maximizing CTR and mitigating harm. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2406_09882 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Harm Mitigation in Recommender Systems under User Preference Dynamics Chee, Jerry Kalyanaraman, Shankar Ernala, Sindhu Kiranmai Weinsberg, Udi Dean, Sarah Ioannidis, Stratis Information Retrieval Computers and Society Machine Learning We consider a recommender system that takes into account the interplay between recommendations, the evolution of user interests, and harmful content. We model the impact of recommendations on user behavior, particularly the tendency to consume harmful content. We seek recommendation policies that establish a tradeoff between maximizing click-through rate (CTR) and mitigating harm. We establish conditions under which the user profile dynamics have a stationary point, and propose algorithms for finding an optimal recommendation policy at stationarity. We experiment on a semi-synthetic movie recommendation setting initialized with real data and observe that our policies outperform baselines at simultaneously maximizing CTR and mitigating harm. |
| title | Harm Mitigation in Recommender Systems under User Preference Dynamics |
| topic | Information Retrieval Computers and Society Machine Learning |
| url | https://arxiv.org/abs/2406.09882 |