Exposure Inequality in People Recommender Systems
The Long-Term Effects
Bibliographic Data
| ID | 7539048 |
|---|---|
| Authors | Francesco Fabbri (0000-0002-9631-1799, Universitat Pompeu Fabra, corresponding author), Maria Luisa Croci (Sapienza University of Rome), Francesco Bonchi (0000-0001-9464-8315), Carlos Castillo (0000-0001-5848-0332, Institució Catalana de Recerca i Estudis Avançats) |
| Year | 2022 |
| Volume | 16 |
| Pages | 194-204 |
| Publication date | 2022-05-31 |
| Peer Reviewed | Yes |
| Open Access | Yes |
| Type | ARTICLE |
| Venue | Proceedings of the International AAAI Conference on Web and Social Media (JOURNAL) |
| Journal identifiers | ISSN: 2162-3449 • E-ISSN: 2334-0770 |
| Publisher | Association for the Advancement of Artificial Intelligence (AAAI) (PUBLISHER) |
| DOI | 10.1609/icwsm.v16i1.19284 |
| OpenAlex | W4312947392 |
| Language | EN |
| Citations received | 4 |
| References cited | 3 |
People recommender systems may affect the exposure that users receive in social networking platforms, influencing attention dynamics and potentially strengthening pre-existing inequalities that disproportionately affect certain groups. In this paper we introduce a model to simulate the feedback loop created by multiple rounds of interactions between users and a link recommender in a social network. This allows us to study the long-term consequences of those particular recommendation algorithms. Our model is equipped with several parameters to control: (i) the level of homophily in the network, (ii) the relative size of the groups, (iii) the choice among several state-of-the-art link recommenders, and (iv) the choice among three different stochastic user behavior models, that decide which recommendations are accepted or rejected. Our extensive experimentation with the proposed model shows that a minority group, if homophilic enough, can get a disproportionate advantage in exposure from all link recommenders. Instead, when it is heterophilic, it gets underexposed. Moreover, while the homophily level of the minority affects the speed of the growth of the disparate exposure, the relative size of the minority affects the magnitude of the effect. Finally, link recommenders strengthen exposure inequalities at the individual level, exacerbating the“rich-get-richer” effect: this happens for both the minority and the majority class and independently of their level of homophily
Affect (linguistics · Class (philosophy · Homophily · Inequality · Recommender system · Term (time · World Wide Web · Complex Network Analysis Techniques · Computer Science · Mathematics · Opinion Dynamics and Social Influence · Psychology · Social Media and Politics · Social Psychology · Artificial Intelligence
| Unique citing works | 4 |
|---|---|
| Citations per year | 2 |
| Citation span | 2024 - 2026 (3) |
| Citation velocity | current |
| Highly cited | No |
| Citation types | Neutral: 4 |