Hidden markov model to predict tourists visited place

2025-11-21

AI Summary

This study addresses the lag in modeling tourist mobility behavior and the lack of dynamic adaptability in tourism demand forecasting. We propose a scalable behavioral modeling framework that integrates grammatical inference with Hidden Markov Models (HMMs). Methodologically, we adapt classical grammatical inference algorithms to large-scale social media data—such as review and photo metadata—to construct a dynamically updatable, structurally editable HMM for accurate next-location prediction at both individual and group levels. Key contributions include: (i) the first application of grammatical inference to tourism trajectory modeling, significantly enhancing sequential pattern discovery; and (ii) a lightweight model update mechanism that balances real-time responsiveness with interpretability. Experiments on a real-world tourism dataset from Paris demonstrate that our approach outperforms conventional HMMs and LSTM baselines, achieving a 12.6% improvement in path prediction accuracy. The framework provides robust technical support for intelligent tourism decision-making and precision marketing.

Technology Category

• Planning, Routing, and Scheduling: Planning with Language Models
• Search and Optimization: Learning to Search
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

• User Modeling, Personalization and Recommendation: Explainable and interpretable methods for personalization
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

Nowadays, social networks are becoming a popular way of analyzing tourist behavior, thanks to the digital traces left by travelers during their stays on these networks. The massive amount of data generated; by the propensity of tourists to share comments and photos during their trip; makes it possible to model their journeys and analyze their behavior. Predicting the next movement of tourists plays a key role in tourism marketing to understand demand and improve decision support. In this paper, we propose a method to understand and to learn tourists' movements based on social network data analysis to predict future movements. The method relies on a machine learning grammatical inference algorithm. A major contribution in this paper is to adapt the grammatical inference algorithm to the context of big data. Our method produces a hidden Markov model representing the movements of a group of tourists. The hidden Markov model is flexible and editable with new data. The capital city of France, Paris is selected to demonstrate the efficiency of the proposed methodology.

Problem

• Predicting tourist movements using social network data analysis
• Adapting grammatical inference algorithms for big data contexts
• Modeling tourist behavior patterns through hidden Markov models

Innovation

• Using hidden Markov model for tourist movement prediction
• Adapting grammatical inference algorithm for big data
• Creating flexible model editable with new data