Point-of-interest recommendation using extended random walk with restart on geographical-temporal hybrid tripartite graph. Issue 1 (2nd January 2023)

• Record Type: Journal Article
• Authors: Taheri, Mozhgan; Farnaghi, Mahdi; Alimohammadi, Abbas; Moradi, Parham; Khoshahval, Samira
• Is Part Of: Journal of spatial science. Volume 68:Issue 1(2023)
• Page Start: 71
• Page End: 89
• Publication Date: 2023-01-02
• Subjects: Location-based social networks (LBSNs) -- graph-based recommendation -- spatio-temporal graph -- random walk with restart (RWR) -- common spatio-temporal preferences; Geographic information systems -- Periodicals; Cartography -- Periodicals; Surveying -- Periodicals; Geodesy -- Periodicals; Photogrammetry -- Periodicals; Cartography; Geodesy; Geographic information systems; Photogrammetry; Surveying; Periodicals; 526.05
• DOI: 10.1080/14498596.2021.1896392
• Languages: English
• ISSNs: 1449-8596

Abstract

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.