Personalized region of interest recommendation through adaptive fusion of multi-dimensional user preferences

Abstract Region of interest (ROI) recommendation is essential for delivering personalized suggestions and optimizing resource allocation. This process involves analyzing users’ historical check-in data within location networks, which helps capture spatial activity preferences and predict regional mo...

Full description

Saved in:
Bibliographic Details
Main Authors: Qing Tang, Shenghua Xu, Zhuolu Wang, Yong Wang, Shichuan Liu, Haiqin Hua
Format: Article
Language:English
Published: SpringerOpen 2025-07-01
Series:Journal of Big Data
Subjects:
Online Access:https://doi.org/10.1186/s40537-025-01224-4
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849333137913413632
author Qing Tang
Shenghua Xu
Zhuolu Wang
Yong Wang
Shichuan Liu
Haiqin Hua
author_facet Qing Tang
Shenghua Xu
Zhuolu Wang
Yong Wang
Shichuan Liu
Haiqin Hua
author_sort Qing Tang
collection DOAJ
description Abstract Region of interest (ROI) recommendation is essential for delivering personalized suggestions and optimizing resource allocation. This process involves analyzing users’ historical check-in data within location networks, which helps capture spatial activity preferences and predict regional movement patterns. To address challenges such as the limited diversity in behavioral distances between user regions, the lack of spatio-temporal correlation in non-contiguous regions, and an inadequate understanding of the variety of user preferences, we examine these preferences from three perspectives: spatio-temporal, social, and category. We then propose a multi-dimensional adaptive fusion method for personalized ROI recommendation. Firstly, the spatial intervals between potential ROIs are calculated by incorporating the shortest paths from geographic maps, directionality preferences, and regional activity patterns. These spatial intervals are then combined with time intervals to derive spatio-temporal preferences, utilizing a two-layer attention mechanism. Next, the social preferences are determined by assessing the influence of social connections and the impact of social networks on the likelihood of a user visiting a region, using a convolutional neural network. In addition, category features are extracted from the users’ historical check-in trajectories, and category preferences are calculated by evaluating the semantic similarity between the Point of Interest (POI) categories and user category features within a region using a multi-layer perceptron. Finally, an adaptive weighting model is introduced to integrate the spatio-temporal, social, and category preferences, assigning individual preference weights to different users to facilitate personalized ROI recommendation. We evaluated the proposed method using Foursquare and Sina Weibo datasets, in conjunction with the state-of-the-art baseline models. The results demonstrate that the proposed approach significantly enhances the critical performance metrics, including Recall, F1-score, and normalized discounted cumulative gain (NDCG).
format Article
id doaj-art-c1c749f9811d4311a0743ea276b7b264
institution Kabale University
issn 2196-1115
language English
publishDate 2025-07-01
publisher SpringerOpen
record_format Article
series Journal of Big Data
spelling doaj-art-c1c749f9811d4311a0743ea276b7b2642025-08-20T03:45:57ZengSpringerOpenJournal of Big Data2196-11152025-07-0112112710.1186/s40537-025-01224-4Personalized region of interest recommendation through adaptive fusion of multi-dimensional user preferencesQing Tang0Shenghua Xu1Zhuolu Wang2Yong Wang3Shichuan Liu4Haiqin Hua5Research Centre of Geo-Spatial Big Data Application, Chinese Academy of Surveying and MappingResearch Centre of Geo-Spatial Big Data Application, Chinese Academy of Surveying and MappingSchool of Geomatics, Liaoning Technical UniversityResearch Centre of Geo-Spatial Big Data Application, Chinese Academy of Surveying and MappingResearch Centre of Geo-Spatial Big Data Application, Chinese Academy of Surveying and MappingDepartment of Radiology, Dongfang Hospital, Beijing University of Chinese MedicineAbstract Region of interest (ROI) recommendation is essential for delivering personalized suggestions and optimizing resource allocation. This process involves analyzing users’ historical check-in data within location networks, which helps capture spatial activity preferences and predict regional movement patterns. To address challenges such as the limited diversity in behavioral distances between user regions, the lack of spatio-temporal correlation in non-contiguous regions, and an inadequate understanding of the variety of user preferences, we examine these preferences from three perspectives: spatio-temporal, social, and category. We then propose a multi-dimensional adaptive fusion method for personalized ROI recommendation. Firstly, the spatial intervals between potential ROIs are calculated by incorporating the shortest paths from geographic maps, directionality preferences, and regional activity patterns. These spatial intervals are then combined with time intervals to derive spatio-temporal preferences, utilizing a two-layer attention mechanism. Next, the social preferences are determined by assessing the influence of social connections and the impact of social networks on the likelihood of a user visiting a region, using a convolutional neural network. In addition, category features are extracted from the users’ historical check-in trajectories, and category preferences are calculated by evaluating the semantic similarity between the Point of Interest (POI) categories and user category features within a region using a multi-layer perceptron. Finally, an adaptive weighting model is introduced to integrate the spatio-temporal, social, and category preferences, assigning individual preference weights to different users to facilitate personalized ROI recommendation. We evaluated the proposed method using Foursquare and Sina Weibo datasets, in conjunction with the state-of-the-art baseline models. The results demonstrate that the proposed approach significantly enhances the critical performance metrics, including Recall, F1-score, and normalized discounted cumulative gain (NDCG).https://doi.org/10.1186/s40537-025-01224-4Location-based social networksRegional movement patternMulti-dimensional user preferencesAdaptive weighting modelROI recommendation
spellingShingle Qing Tang
Shenghua Xu
Zhuolu Wang
Yong Wang
Shichuan Liu
Haiqin Hua
Personalized region of interest recommendation through adaptive fusion of multi-dimensional user preferences
Journal of Big Data
Location-based social networks
Regional movement pattern
Multi-dimensional user preferences
Adaptive weighting model
ROI recommendation
title Personalized region of interest recommendation through adaptive fusion of multi-dimensional user preferences
title_full Personalized region of interest recommendation through adaptive fusion of multi-dimensional user preferences
title_fullStr Personalized region of interest recommendation through adaptive fusion of multi-dimensional user preferences
title_full_unstemmed Personalized region of interest recommendation through adaptive fusion of multi-dimensional user preferences
title_short Personalized region of interest recommendation through adaptive fusion of multi-dimensional user preferences
title_sort personalized region of interest recommendation through adaptive fusion of multi dimensional user preferences
topic Location-based social networks
Regional movement pattern
Multi-dimensional user preferences
Adaptive weighting model
ROI recommendation
url https://doi.org/10.1186/s40537-025-01224-4
work_keys_str_mv AT qingtang personalizedregionofinterestrecommendationthroughadaptivefusionofmultidimensionaluserpreferences
AT shenghuaxu personalizedregionofinterestrecommendationthroughadaptivefusionofmultidimensionaluserpreferences
AT zhuoluwang personalizedregionofinterestrecommendationthroughadaptivefusionofmultidimensionaluserpreferences
AT yongwang personalizedregionofinterestrecommendationthroughadaptivefusionofmultidimensionaluserpreferences
AT shichuanliu personalizedregionofinterestrecommendationthroughadaptivefusionofmultidimensionaluserpreferences
AT haiqinhua personalizedregionofinterestrecommendationthroughadaptivefusionofmultidimensionaluserpreferences