High-frequency and timely tourism demand forecasting of fine-grained attractions is an effective tool that helps tourism stakeholders make decisions and formulate strategies. However, there are limitations due to the external sensitivity of tourism demand. This research integrated news coverage with other psychosocial variables to comprehensively explore the impact of social unrest on tourism demand. Topic modelling was applied to identify tourism news topics and potential meanings. Sentiment classification was used to convert news into structured data. Sentiment indices and quantities constituted a composite news term. The empirical results showed that the comprehensive inclusion of external elements, especially news coverage, can significantly improve the prediction performance. K-Nearest Neighbour with the news term yielded the best results.

Urban tourism imagery is an essential factor affecting the competitiveness of cities. However, most existing studies use small data methods such as interviews and questionnaires to explore tourists’ perceptions of cities without combining big data for analysis. In addition, there is relatively little research on the tourism imagery of coastal cities. Therefore, this study analyzes the data from 523 travelogues from a three-dimensional perspective of identity, structure, and meaning, using methods such as BERTopic, aiming to explore the tourism imagery of coastal cities perceived by tourists. The results show the following: (1) In terms of identity, Sanya’s urban tourism imagery has the attribute of “external explicit-internal implicit”, which satisfies tourists’ visual and spiritual experiences. (2) Regarding structure, Sanya has a clear regional division of imagery and a core–edge diffusion distribution among regions. (3) Regarding meaning, tourists’ attitudes toward Sanya are polarized. Positive emotions predominate in the overall perception of meaning, but 25% of the negative emotions require urgent attention. This study provides a reference for the sustainable development of tourism cities and the marketing management of destinations.

The goal of investors in the hotel business is to maximize profits, and the price is an important means of achieving this goal. This has attracted many scholars to study the spatiotemporal relationship between hotel room prices and their possible influencing factors from different perspectives. However, most existing studies adopt the linear assumption of the hedonic model, with limited features and a lack of feature selection procedures. Additionally, there are few forecasts of hotel pricing from a spatial perspective. To overcome these gaps, this study adopts linear and nonlinear machine learning methods based on the “big data” of Sanya City to explore the influencing factors of budget hotel pricing. Based on the spatial perspective, 81 potential factors were considered. They are further selected using a feature extraction model called recursive feature elimination. Six machine-learning algorithms were evaluated and compared: random forest, extreme gradient boosting, multi-linear regression, support vector regression, multilayer perceptron regression, and K-nearest neighbor regression. The optimal value was used to further calculate the feature importance. They disclosed 40 important impact characteristics and predicted the spatial distribution of hotel pricing.

Digital transformation is reshaping tourism markets by enabling destinations to communicate with prospective visitors, strengthen their online reputation, and present distinctive destination experiences through digitally connected environments. This study examines the relationships among social media marketing efforts, e-reputation, perceived authentic destination experience, destination image, and destination behavioral intention (DBI) in emerging destinations along the China-Pakistan Economic Corridor (CPEC). Grounded in the Stimulus–Organism–Response (S-O-R) framework and Destination Image Theory, the study conceptualizes destination image as an internal cognitive-affective evaluative state linking digital, reputational, and experiential destination-related stimuli with behavioral intention. Data were collected from 385 respondents familiar with CPEC destinations and analyzed using Partial Least Squares Structural Equation Modeling (PLS-SEM). The results indicate that social media marketing efforts, e-reputation, and perceived authentic destination experience are positively associated with destination image, which is in turn positively associated with destination behavioral intention. Statistically significant indirect associations through destination image are also consistent with the theoretically proposed mediating pathways. Importance–Performance Map Analysis further identifies perceived authentic destination experience as the relatively most important antecedent among the examined exogenous constructs within the estimated model, while e-reputation exhibits comparatively lower performance and may therefore warrant managerial attention. The study contributes to digital destination-marketing research by integrating digital communication, socially generated reputation, experiential authenticity, and destination image within a common evaluative framework in an emerging tourism context. Although sustainable tourism development was not directly measured, the findings may inform sustainability-oriented destination management when visitor interest is considered alongside environmental capacity, cultural preservation, community interests, and long-term destination-development objectives.