These tools will no longer be maintained as of December 31, 2024. Archived website can be found here. PubMed4Hh GitHub repository can be found here. Contact NLM Customer Service if you have questions.


Pubmed for Handhelds

PUBMED FOR HANDHELDS

Search MEDLINE/PubMed

  • Title: Value evaluation of cultural tourism tourists' psychological expectation based on machine learning data mining.
    Author: Pai CH, Xu S, Jin J, Shang Y.
    Journal: Front Psychol; 2022; 13():943071. PubMed ID: 36003117.
    Abstract:
    The era of smart tourism has arrived. In the context of big data information, based on the thinking of the entire tourism activity, it is worth thinking about the role of tourism information in tourism activities. This paper proposes a method for evaluating the psychological expectations of tourist destinations by applying the quality function configuration. According to the needs of tourists, the relevant product characteristics of the tourist destination are selected, an evaluation quality house is established, and various relationships within the quality house are weighed, and established a mathematical model for the evaluation of tourists' psychological expectations in tourist destinations. Bringing the methods of machine learning (ML) and data mining (DM) into the research of tourists' psychological expectation value evaluation, ML is one of the main methods to solve the problem of DM. ML is the process of using the system itself to improve itself, therefore, ML is widely used in data mining. The research combines psychology and tourism research, through empirical research, to establish a structural equation model. It analyzes the influence of tourism information on tourists' behavioral decisions, increases the media's variable expectations of tourism, and uses tourist satisfaction and behavior as dependent variables. The results showed that the effect of tourism information on tourists is significantly greater than the expected effect (p = 0.510, P is significant at 0.001 level) than the effect of tourist satisfaction (p = 0.290, P is significant at 0.05 level). Therefore, in order to create good expectations for tourists, the general image of a tourist destination must match the actual local conditions. Using the support vector machine algorithm with the introduction of optimization mechanism to train the feature set of the user data, and then predict the links in Sina Weibo, and obtain higher prediction accuracy and prediction speed. The psychological expectation evaluation model of tourists in tourist destinations can effectively calculate the perceived value of psychological expectation evaluation of tourists in tourist destinations, and help tourists choose reasonable and satisfactory travel plans.
    [Abstract] [Full Text] [Related] [New Search]