A Partition-Based Partial Personalized Model for Points-of-Interest Recommendations

Elahe Naserian, Xinheng Wang*, Keshav P. Dahal, Jose M. Alcaraz-Calero, Honghao Gao

*Corresponding author for this work

Research output: Contribution to journalArticlepeer-review

10 Citations (Scopus)


Location-aware recommendation is considered as one of human behavior cognitive analyses in the world of human-machine-environment system. The development of 5G technology and ubiquitous mobile devices has led to the emergence of a new online platform, location-based social networks (LBSNs), which allows users to share their locations. The essential feature of LBSNs is to provide users with location recommendations that help them explore new places and also to make LBSNs more prevalent to users. Most of the existing research is focusing on the introduction of new features and how these new features affect the check-in behaviors of the users. In addition, the dependencies between each feature and the probability of a user visiting the site is always a principle to follow. However, a user's decision could be determined by considering several features at the same time. When a full model is applied by considering all the features, an overfitting problem could be occurred owing to the lack of sufficient data for each individual user. In this article, an intermediate solution was proposed to address all of these problems by fragmenting the model into several partial models, where each partial model is responsible for a few features. An additive strategy was also implemented to support the development of personalized partial models. Furthermore, a partition-based approach was introduced to explore the hidden patterns from the geographically clustered check-in data. The performance of the approaches has been evaluated by using the data sets from Foursquare and it demonstrates that the proposed approach outperforms the state-of-the-art approaches.

Original languageEnglish
Pages (from-to)1223-1237
Number of pages15
JournalIEEE Transactions on Computational Social Systems
Issue number5
Publication statusPublished - 1 Oct 2021


  • Human behavior analysis
  • location recommendation
  • location-based social network (LBSN)
  • point-of-interest (POI)

Cite this