Accurate POI recommendation for random groups with improved graph neural networks and a multi-negotiation model
Abstract In recent years, the growing prevalence of group activities has brought increased interest in Point of Interest (POI) recommendations for groups. While significant progress has been made in recommending POIs for fixed groups, research on personality-aware recommendations for random groups h...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-03-01
|
| Series: | Scientific Reports |
| Subjects: | |
| Online Access: | https://doi.org/10.1038/s41598-025-91805-3 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Abstract In recent years, the growing prevalence of group activities has brought increased interest in Point of Interest (POI) recommendations for groups. While significant progress has been made in recommending POIs for fixed groups, research on personality-aware recommendations for random groups has been still largely untouched. Moreover, existing works recommend a POI list for a group and the group makes further choice of the optimal POI, which results in poor user experience. To solve the above problems, this work proposes a model for Accurate POI Recommendation for Random Groups with improved Graph Neural Networks and a Multi-negotiation Model (termed as APRRGM). Specifically, APRRGM first produces the fitted feature of the random group based on group members’ personalities and their POI interaction data. Then, APRRGM learns POIs’ features from the bipartite graph of user and POI with an improved Graph Neural Networks (GNN) while considering members’ personalities. Next, APRRGM recommends a POI sequence based on the fitted feature of the random group and the features of POIs. Finally, based on the recommended POI list and members’ personalities, APRRGM determines the optimal POI for the random group with an improved multi-negotiation model. The extensive experiments conducted on three public benchmark datasets (Yelp, Gowalla, and Foursquare) have proved that APRRGM performs better than other baseline models. |
|---|---|
| ISSN: | 2045-2322 |