Author:
Moayedikia Alireza,Jahani Hamed,Rahman Md Anisur,Ong Kok Leong
Abstract
AbstractUsers utilize Location-Based Social Networks (LBSNs) to check into diverse venues and share their experiences through ratings and comments. However, these platforms typically feature a considerably larger number of locations than users, resulting in a challenge known as insufficient historical data or user-location matrix sparsity. This sparsity arises because not all users can check into all available locations on a given LBSN, such as Yelp. To address this challenge, this paper proposes combining Spectral Clustering with a three-layered location recommendation model to develop a recommender system named LSC, applied to Yelp datasets. LSC leverages various information, including users’ check-in data, demographics, location demographics, and users’ friendship network data, to train the recommender system and generate recommendations. Evaluation of LSC’s performance utilizes the Yelp dataset and several comparison metrics, such as accuracy, RMSE, and F1-score. The results demonstrate that our proposed algorithm delivers reliable and significant performance improvements across various evaluation metrics compared to competing algorithms.
Funder
Swinburne University of Technology
Publisher
Springer Science and Business Media LLC
Reference46 articles.
1. Alshammari M, Stavrakakis J, Takatsuka M (2021) Refining a k-nearest neighbor graph for a computationally efficient spectral clustering. Pattern Recogn 114:107869
2. Alves P, Martins H, Saraiva P, Carneiro J, Novais P, Marreiros G (2023) Group recommender systems for tourism: how does personality predict preferences for attractions, travel motivations, preferences and concerns? Marreiros, g 33(5):1141–1210
3. Bai L, Qi M, Liang J (2023) Spectral clustering with robust self-learning constraints. Artif Intell 320:103924
4. Behera G, Nain N (2023) The state-of-the-art and challenges on recommendation system’s: principle, techniques and evaluation strategy. SN Comp Sci 4(5):677
5. Cai W, Wang Y, Lv R, Jin Q (2019) An efficient location recommendation scheme based on clustering and data fusion. Comput Electr Eng 77:289–299