This study aims to explore thematic influences on theme park visitors' satisfaction through user‐generated data. To this end, we first used an unsupervised machine learning method, structural topic modeling, and analyzed 112,000 reviews post by visitors to Shanghai Disney Resort from June 16, 2016 to March 4, 2022. Our findings are of great significance for reflecting consumer behavior through user‐generated data. Specifically, we find that visitors' satisfaction is highly related to service in the theme park and their playing feeling, and early tourists pay more attention to the experience of specific playing items while later tourists focus on the overall playing experience. In addition, an empirical study is conducted by treating the ratings associated with each review as dependent variable and each topic represented by comments as independent variables, which shows that the relationship between the customer reviews and ratings by tourists becomes less pronounced over time. In other words, as time goes, customers review can reflect their subjective feelings or experience, but the rating is not. We discover the “dynamics” of user‐generated data over time and gain a better understanding of the aspects and concerns of visitors' satisfaction over time. The findings of the study contribute to the literature on tourism, service, and consumer behavior while also providing valuable practical implications.

This paper proposes a large-scale group decision-making model with cooperative behavior based on social network analysis considering propagation of decision-makers’ preference, which is applicable for large-scale group decision-making problems in social network contexts. The main contributions of our research are three aspects. Firstly, a novel calculation method of cooperative degree, hesitant degree, and noncooperative degree is developed, which considers both the network status and the preference for each DM, and thereby it can better represent the current state for each DM. Then, the determination method of each DM’s weight is presented, which considers both the individual network centrality and preference similarity degree. In addition, the score for the current cooperation situation is performed, and the improvement algorithm of the increase of cooperative degree and the decrease of noncooperative degree is designed to enhance the quality of the decision-making results. Finally, the proposed model has demonstrated the validity and superiority based on the comparative and sensitive analysis through a practical example.

The aim of this study was to explore the causes of tourists’ lesser enjoyment of theme parks through an unsupervised machine learning approach—structural topic modelling. Specifically, the research extracted a comprehensive list of discussion topics about the travel experience of tourists through the analysis of 112,000 customer reviews released by visitors to the Shanghai Disney Resort from 16 June 2016 to 4 March 2022. Then, we used sentiment analysis to distinguish positive and negative topics and to explore the relationship between tourists who buy different ticket types and sentiments in negative topics. The results show that problems such as “parking,” “service attitude,” “recommendation feeling,” “experience comparison,” and “entrance” may be the main reasons for an unpleasant experience. In addition, we also found that when tourists travel in groups (e.g., via family tickets), customers feel unhappy because of parking and fast track problems. Moreover, when tourists travel alone or with small groups, staff service attitudes, experience comparisons, and entrance processes are the sources of greater concern. Our findings can help theme park managers to better understand the expectations of tourists and take effective measures to tackle issues causing customer dissatisfaction, and they can also contribute to theme park studies in tourism management.

During the normalization stage of the COVID-19 epidemic prevention and control, the safety threats caused by improper epidemic prevention measures of airlines have become the primary concern for air passengers. Negative e-WOM related to safety perception obtained based on online multimodal reviews of travel websites has become an important decision-making basis for potential air passengers when making airline choices. This study aims to examine the relationship between potential air passengers’ negative safety perception and the usefulness of online reviews, as well as to test the moderating effect of review modality and airline type. It also further explores the effectiveness and feasibility of applying big data sentiment analysis to e-WOM management. To this end, the theoretical model of negative safety perception, review modality, and airline type affecting review usefulness was constructed. Then we select 10 low-cost airlines and 10 full-service airlines, respectively, according to the number of reviews sorted by the TripAdvisor website, and use crawling techniques to obtain 10,485 reviews related to COVID-19 safety of the above companies from December 2019 to date, and conduct safety perception sentiment analysis based on Python’s Textblob library. Finally, to avoid data overdispersion, the model is empirically analyzed by negative binomial regression using R software. The results indicate that (1) Negative safety perception significantly and negatively affects review usefulness, that is, extreme negative safety perception can provide higher review usefulness for potential air passengers. (2) Review modality and airline type have a significant moderating effect on the relationship between negative safety perception and review usefulness, in which multimodal reviews and full-service airlines both weakened the negative impact of negative safety perception on review usefulness. The theoretical model in this paper is both an extension of the application of big data sentiment analysis techniques and a beneficial supplement to current research findings of e-WOM, providing an important reference for potential air passengers to identify useful reviews accurately and thus reduce safety risks in online decision-making.

By embedding blockchain technology into the process of standardized production of agricultural products, we use the characteristics of blockchain such as tamper-proof, decentralization, and consensus mechanism to solve the trust problem, responsibility problem, and quality problem in the process of standardized production of agricultural products. These three subjects in the process of standardized production of agricultural products are analysed, and the three-party game model among agricultural producers, government, and consumers is constructed with the help of the evolutionary game method, and the influence of each subject in different strategies is analysed, and the inference results are simulated and experimented with MATLAB 2016 software. The results show that the standardized production of agricultural products embedded in blockchain needs to meet three basic conditions: agricultural producers need to ensure that the sum of production costs and penalties for noncompliance following technological innovation using blockchain is less than the sum of production costs and penalties for noncompliance for traditional agricultural products; the difference value between strict and loose government regulation needs to be smaller than the amount of penalty for violation of standardized production of agricultural products embedded in blockchain; the cost of whistleblowing for consumers needs to be less than the number of penalties incurred for production violations when agricultural producers choose standardized production of agricultural products embedded in blockchain. It is also found that the violation ratio of agricultural producers, the social welfare of strict government regulation, and the whistleblowing benefit of consumers are the key factors affecting the standardized production of agricultural products, and the analysis of the influence of the key factors points to the direction for promoting the standardized production of agricultural products.