Open AccessRelational POI recommendation model combined with geographic information
Author(s) -
Ké Li,
Haitao Wei,
Xiaohui He,
Zhigang Tian
Publication year - 2022
Publication title -
plos one
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.99
H-Index - 332
ISSN - 1932-6203
DOI - 10.1371/journal.pone.0266340
Subject(s) - point of interest , computer science , geographic information system , similarity (geometry) , information retrieval , cosine similarity , data mining , geospatial analysis , cluster analysis , location based service , perspective (graphical) , precision and recall , data science , geography , artificial intelligence , cartography , telecommunications , image (mathematics)
Point of interest (POI) recommendation is a popular personalized location-based service. This paper proposes a Geographic Personal Matrix Factorization (GPMF) model that makes effective use of geographic information from the perspective of the relationship between POIs and users. This model considers the role of geographic information from multiple perspectives based on the locational relationship among users, the distributional relationship between users and POIs, and the proximity and clustering relationship among POIs. The GPMF mines the influence of geographic information on different objects and carries out unique modeling through cosine similarity, non-linear function, and k nearest neighbor (KNN). This study explored the influence of geographic information on POI recommendation through extensive experiments with data from Foursquare. The result shows that GPMF performs better than the commonly used POI recommendation algorithm in terms of both precision and recall. Geographic information through proximity relations effectively improves the recommendation algorithm.