Article: Sports tourism information recommendation modelling based on user preference fine granularity and improved LSTM network Journal: International Journal of Wireless and Mobile Computing (IJWMC) 2026 Vol.30 No.4 pp.382 - 394 Abstract: Currently, there are issues such as insufficient user data in the sports tourism information recommendation, which leads to a lack of fine-grained analysis of user preferences and affects the recommendation effectiveness. To address these issues, this paper proposes to combine user preference fine granularity, and construct a sports tourism recommendation model based on Knowledge Graph (KG) combined Whale Optimisation Algorithm (WOA) optimised Bidirectional Long Short-Term Memory (BiLSTM). Through this model, personalised recommendations of sports tourism information can be achieved, improving the recommendation effect of sports tourism information. Experimental results show that Recall@k and NDCG@k indexes of the proposed model are increased by 6.83% and 9.05%, respectively, which are significantly better than comparison models. Therefore, the designed model has higher recommendation precision, which can achieve fine-grained analysis of user preferences and accurate recommendation of tourism information, meet the practical needs of sports tourism information recommendation, and has effectiveness. Inderscience Publishers - linking academia, business and industry through research

Title: Sports tourism information recommendation modelling based on user preference fine granularity and improved LSTM network

Authors: Liying He; Huimin Zhang; Yaping Wang

Addresses: Sports Department, Pearl River College, Tianjin University of Finance and Economics, Hexi, Tianjing, China ' Sports Department, Pearl River College, Tianjin University of Finance and Economics, Hexi, Tianjing, China ' Sports Department, Pearl River College, Tianjin University of Finance and Economics, Hexi, Tianjing, China

Abstract: Currently, there are issues such as insufficient user data in the sports tourism information recommendation, which leads to a lack of fine-grained analysis of user preferences and affects the recommendation effectiveness. To address these issues, this paper proposes to combine user preference fine granularity, and construct a sports tourism recommendation model based on Knowledge Graph (KG) combined Whale Optimisation Algorithm (WOA) optimised Bidirectional Long Short-Term Memory (BiLSTM). Through this model, personalised recommendations of sports tourism information can be achieved, improving the recommendation effect of sports tourism information. Experimental results show that Recall@k and NDCG@k indexes of the proposed model are increased by 6.83% and 9.05%, respectively, which are significantly better than comparison models. Therefore, the designed model has higher recommendation precision, which can achieve fine-grained analysis of user preferences and accurate recommendation of tourism information, meet the practical needs of sports tourism information recommendation, and has effectiveness.

Keywords: user preference fine granularity; knowledge graph; WOA algorithm; BiLSTM network; sports tourism information recommendation.

DOI: 10.1504/IJWMC.2026.154167

International Journal of Wireless and Mobile Computing, 2026 Vol.30 No.4, pp.382 - 394

Received: 28 Mar 2025
Accepted: 17 Jul 2025
Published online: 15 Jun 2026 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article

Title: Sports tourism information recommendation modelling based on user preference fine granularity and improved LSTM network

Keep up-to-date