Search

Tourism is vital to national economic growth and fulfilling individuals' spiritual pursuits. However, traditional scenic recommendation algorithms must improve accuracy, susceprecommended route personalizationtion of recommended tour routes, and suboptimal tour value. This study presents a UGC text mining-based travel recommendation method to address these problems. To begin with, the proposed method utilizes text mining techniques to enrich scenic tag data and introduces the recommendation algorithm based on fuzzy label-matching user-item characteristics (FLMC). Additionally, we incorporate scenic attributes and travel time between scenics to identify four key attributes that impact scenic selection in tour routes. Users' subjective preferences for these attributes are calculated, and objective weights derived from information entropy are used to determine combination weights for scenic selection. This ensures a more personalized and optimized tour route. Lastly, the proposed method features a tour route ranking method that selects the highest-scoring route as the recommended option. This approach enhances the overall quality of the recommended tour routes. Through experimentation with 240,194 reviews of 369 scenics in Beijing, in the attraction recommendation scenario, the proposed FLMC algorithm achieves up to 75.40% accuracy, which is higher than the other three compared algorithms (46.48%, 35.90%, and 32.98%). In the travel route recommendation scenario, the proposed method has a route gain value of up to 1.57 and a user experience value of recommended route personalizationd compared to the other three compared algorithms (1.03, 0.9; 0.95, 0.53; 1.12, 0.85). These results highlight the significant potential of the proposed method in improving the personalization of travel recommendations and enhancing tourist experiences. [ABSTRACT FROM AUTHOR]

• Novel multi-modal transport recommendation via graph neural networks. • Models travel behaviors with spatial and temporal data integration. • Introduces a contrastive learning framework to reduce bias. • CDHGNN: New de-biased recommendation framework tested in Beijing. • Demonstrates superiority over existing methods using 300,000 user records. Conventional uni-modal transportation recommendation systems focused on single modes of transportation are limited in providing satisfactory solutions since passengers often undertake journeys involving multiple modes. Multi-modal transportation recommendation systems are becoming increasingly popular within navigation applications. However, these systems face challenges from biased raw data, data sparsity and long-tail distribution, as well as complexities in representing large-scale graph structures, which collectively hinder their optimal performance. This study introduces a novel approach for enhancing multi-modal transportation recommendation systems: the C ontrastive D e-biased H eterogeneous G raph N eural N etwork (CDHGNN). By integrating contrastive learning, the model generates augmented samples to mitigate bias and overcome the data-skewing problem. The heterogeneous graph neural network adaptively captures temporal and spatial patterns among users and locations, as well as spatial adjacency and attribute relations, leading to enhanced representations of nodes, and consequently, improved model performance. The proposed method was evaluated using real-world data from over 300,000 users' records in Beijing over two months in 2018. The extensive experiments demonstrate that the approach outperforms four contemporary state-of-the-art methods. The results underscore the potential of the CDHGNN in large-scale city-level problems in practical applications, revealing a promising advancement for multi-modal transportation recommendation systems. [ABSTRACT FROM AUTHOR]