A MAS-Based Approach for POI Group Recommendation in LBSN

Silvia Schiaffino (1, 2) , Daniela Godoy (1, 2) , J. Andrés Díaz Pace (1, 2) , Yves Demazeau (3, 4)

1 ISISTAN - Instituto Superior de Ingeniería de Software Tandil [Buenos Aires]
2 UNICEN - Universidad Nacional del Centro de la Provincia de Buenos Aires [Buenos Aires]
3 LIG - Laboratoire d'Informatique de Grenoble
4 CNRS - Centre National de la Recherche Scientifique

Location-based recommender systems (LBRS) suggest friends, events, and places considering information about geographical locations. These recommendations can be made to individuals but also to groups of users, which implies satisfying the group as a whole. In this work, we analyze dierent alternatives for POI group recommendations based on a multi-agent system consisting of negotiating agents that represent a group of users. The results obtained thus far indicate that our multi-agent approach outperforms traditional aggregation approaches, and that the usage of LBSN information helps to improve both the quality of the recommendations and the eciency of the recommendation process.

Mots clés: group recommender systems; location-based social networks; multi-agent systems; negotiation

Domaines: Système multi-agents [cs.MA]; Intelligence artificielle [cs.AI]

Silvia Schiaffino, Daniela Godoy, J. Andrés Díaz Pace, Yves Demazeau. A MAS-Based Approach for POI Group Recommendation in LBSN. 18th International Conference on Practical Applications of Agents and Multi-Agent Systems, PAAMS’20, Oct 2020, L'Aquila, Italy. pp.238-250, ⟨10.1007/978-3-030-49778-1_19⟩. ⟨hal-02964868⟩