Research on Slow Travel Consumer Behavioral Feature Extraction and Decision Support Based on Intelligent Data Analysis

This study focuses on the field of slow tourism, aiming to deeply excavate the intrinsic characteristics of slow tourism consumers through intelligent data analysis technology and give corresponding decision support. First, based on the results of data cleaning, data sampling, and feature preprocessing, the key data set for consumer subjects is established. Second, the ant colony algorithm is invoked to realize feature fusion extraction based on the classification results of subject data and the mining results of object data. Next, the interest feature extraction model was established based on the extracted behavioral features. Finally, decision support is formed based on the constructed interest degree matrix. The number of dissatisfied decision-makers under the perceived usefulness and perceived intrusion dimensions is 45 and 49, respectively, which accounts for a relatively small number of people. The number of satisfied people in the decision support formed by the method of this paper is predominant.