Hybrid POI group recommender system based on group type in LBSN

被引:10
作者
Sojahrood, Zahra Bahari [1 ,2 ]
Taleai, Mohammad [1 ,3 ,4 ]
Cheng, Hao [2 ]
机构
[1] KN Toosi Univ Technol, Fac Geomat, Tehran, Iran
[2] Leibniz Univ Hannover, Inst Cartog & Geoinformat, Hannover, Germany
[3] UNSW, Sch Built Environm, GRID, ADA, Sydney, Australia
[4] KN Toosi Univ Technol, Fac Geodesy & Geomat Engn, Tehran, Iran
关键词
Cold start; Group-based methods; Aggregation-based strategy; Probabilistic Matrix Factorization (PMF); DESIGN;
D O I
10.1016/j.eswa.2023.119681
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Point of interest (POI) group recommender systems (GRSs) aim to suggest places for a group of users. Compared to recommender systems for individual users, GPRs are more challenging due to the complexity of groups formed by members with conflicting interests and preferences. To cope with this challenge, the current POI GRSs utilize strategies-based approaches, e.g., group history, aggregation of group members' history, and further improved aggregation with the consideration of group members' interactions. However, these GRSs still suffer from low accuracy and the cold-start problem for groups with insufficient historical information. Moreover, rare studies have attempted to compare/combine the different strategies for GRSs. In this paper, to achieve the collective advantages over existing GRSs, a hybrid method performs switching among different recommendation strategies based on the criteria of group type (persistent and ephemeral regarding group history) and homogeneity (sim-ilarity of group members' interests and preferences) is proposed. A dataset from the city of Ankara that contains user and group check-ins, was extracted from the Foursquare Swarm application to evaluate the performance of the proposed method. This hybrid method outperforms the single strategies using various algorithms by improving at least 30% in precision@5 and 25% in recall@5 across all the test groups. The empirical results demonstrate that the introduced hybrid solution, which automatically identifies group type and homogeneity, can quickly and effectively go beyond the restrictions of the individual strategies for GRSs.
引用
收藏
页数:9
相关论文
共 42 条
[11]  
Felfernig A, 2018, GROUP RECOMMENDER SY, P59, DOI DOI 10.1007/978-3-319-75067-5_3
[12]   A negotiation framework for heterogeneous group recommendation [J].
Garcia, Inma ;
Sebastia, Laura .
EXPERT SYSTEMS WITH APPLICATIONS, 2014, 41 (04) :1245-1261
[13]   On the design of individual and group recommender systems for tourism [J].
Garcia, Inma ;
Sebastia, Laura ;
Onaindia, Eva .
EXPERT SYSTEMS WITH APPLICATIONS, 2011, 38 (06) :7683-7692
[14]   HGGC: A hybrid group recommendation model considering group cohesion [J].
Jeong, Hyun Ji ;
Kim, Myoung Ho .
EXPERT SYSTEMS WITH APPLICATIONS, 2019, 136 :73-82
[15]   Personalized hybrid recommendation for group of users: Top-N multimedia recommender [J].
Kassak, Ondrej ;
Kompan, Michal ;
Bielikova, Maria .
INFORMATION PROCESSING & MANAGEMENT, 2016, 52 (03) :459-477
[16]   Context-Aware Group-Oriented Location Recommendation in Location-Based Social Networks [J].
Khazaei, Elahe ;
Alimohammadi, Abbas .
ISPRS INTERNATIONAL JOURNAL OF GEO-INFORMATION, 2019, 8 (09)
[17]  
Kompan M, 2014, COMPUT INFORM, V33, P446
[18]   Towards comprehensive profile aggregation methods for group recommendation based on the latent factor model [J].
Le Nguyen Hoai Nam .
EXPERT SYSTEMS WITH APPLICATIONS, 2021, 185
[19]   A hybrid approach for improving predictive accuracy of collaborative filtering algorithms [J].
Lekakos, George ;
Giaglis, George M. .
USER MODELING AND USER-ADAPTED INTERACTION, 2007, 17 (1-2) :5-40
[20]   Hybrid Deep Framework for Group Event Recommendation [J].
Li, Ruichang ;
Zhu, Honglei ;
Fan, Liao ;
Song, Xuekun .
IEEE ACCESS, 2020, 8 :4775-4784