Accurate forecasting of tourist demand is important to both business practitioners and government policymakers. In the past decade of rapid development of deep learning, many artificial intelligence methods or deep learning models have been built to improve prediction accuracy. But data-driven end-to-end deep network models usually require large data sets to support. For tourism forecasting, the sample is insufficient and many models are difficult to apply. In this article, we propose a novel hybrid model GM-LSTM, which combines the advantages of gray models and neural networks to achieve self-adaptive prediction with small samples. Specifically, the overall trend of tourism demand is captured by a first-order gray model and the non-linear residual fluctuation is characterized using a long short-term memory (LSTM) network with a rolling mechanism. The model is validated through a case study of up to 38 years of data on annual international tourist arrivals in Xi’an, China. The proposed GM-LSTM model achieved a predicted MAPE value of 11.88%, outperforming other time series models. The results indicate that our proposed hybrid model is accurate and efficient.

With the exponential growth of online review platforms, understanding user preferences and interests in the tourism domain has become increasingly critical for businesses and service providers. However, extracting meaningful insights from the vast amount of available data poses a significant challenge. Traditional methods often struggle to capture the nuanced and hierarchical nature of user interests within the tourism domain. This paper pioneers the integration of domain information modeling technology into the realm of online review information mining, presenting a novel approach to constructing a user tourism interest model. Unlike existing methods, which primarily rely on flat or simplistic representations of user data, our approach leverages the hierarchical structure inherent in tourism domain information modeling. By harnessing big data within the tourism domain, we construct hierarchical tourism attributes and apply a conditional random field model along with an affective dictionary to facilitate the hierarchical mining of user travel interest information. This culminates in the establishment of a comprehensive user travel interest model using advanced information modeling techniques. Building upon this foundation, we further propose a dynamic user travel interest model, showcasing its adaptability and responsiveness to changing user preferences. Finally, we validate the accuracy and effectiveness of our model through simulation experiments within a user travel recommendation system, demonstrating significant improvements over traditional methods.