Abstract
Previous studies neglected the impact of shared spatio-temporal interests in the Point of Interest (POI) recommendation. The proposed GHTG-ERWR method simultaneously models shared spatio-temporal preferences of users, the dynamics of users’ behavior, and the geographical effect for POI recommendation. It is composed of an Extended Random Walk with Restart (ERWR) algorithm that works on a Geographical-temporal Hybrid Tripartite Graph (GHTG). The method overcomes shortcomings of prior approaches by employing users’ joint preferences over time and space through the auxiliary information derived from location-session and session-location edges. Experimental results on Gowalla and Weeplaces datasets proved the feasibility of the approach.
Original language | English |
---|---|
Pages (from-to) | 1-19 |
Number of pages | 19 |
Journal | Journal of spatial science |
Early online date | 22 Mar 2021 |
DOIs | |
Publication status | Published - 22 Mar 2021 |
Keywords
- Location-based social networks
- Graph-based recommendation
- Spatio-temporal
- Graph
- Random walk
- Common spatio-temporal preferences
- ITC-ISI-JOURNAL-ARTICLE
- ITC-HYBRID
- UT-Hybrid-D