Exploring destination image through online reviews: an augmented mining model using latent Dirichlet allocation combined with probabilistic hesitant fuzzy algorithm

Abstract

PurposeIn the era of information overload, the density of tourism information and the increasingly sophisticated information needs of consumers have created information confusion for tourists and scenic-area managers. The study aims to help scenic-area managers determine the strengths and weaknesses in the development process of scenic areas and to solve the practical problem of tourists' difficulty in quickly and accurately obtaining the destination image of a scenic area and finding a scenic area that meets their needs.Design/methodology/approachThe study uses a variety of machine learning methods, namely, the latent Dirichlet allocation (LDA) theme extraction model, term frequency-inverse document frequency (TF-IDF) weighting method and sentiment analysis. This work also incorporates probabilistic hesitant fuzzy algorithm (PHFA) in multi-attribute decision-making to form an enhanced tourism destination image mining and analysis model based on visitor expression information. The model is intended to help managers and visitors identify the strengths and weaknesses in the development of scenic areas. Jiuzhaigou is used as an example for empirical analysis.FindingsIn the study, a complete model for the mining analysis of tourism destination image was constructed, and 24,222 online reviews on Jiuzhaigou, China were analyzed in text. The results revealed a total of 10 attributes and 100 attribute elements. From the identified attributes, three negative attributes were identified, namely, crowdedness, tourism cost and accommodation environment. The study provides suggestions for tourists to select attractions and offers recommendations and improvement measures for Jiuzhaigou in terms of crowd control and post-disaster reconstruction.Originality/valuePrevious research in this area has used small sample data for qualitative analysis. Thus, the current study fills this gap in the literature by proposing a machine learning method that incorporates PHFA through the combination of the ideas of management and multi-attribute decision theory. In addition, the study considers visitors' emotions and thematic preferences from the perspective of their expressed information, based on which the tourism destination image is analyzed. Optimization strategies are provided to help managers of scenic spots in their decision-making.

Tracking Investment Intentions: The Impact of Information, Confusion, and Avoidance Attitude in Stock Investment Applications

“…Users who willingly invest more time and effort in the exploration and processing of information are less prone to experiencing confusion compared to their counterparts who exhibit a lesser inclination to do so (Lu et al, 2016). The burgeoning volume of available information and the intricate nature of consumer information requirements have been demonstrated to induce consumer confusion (Luo et al, 2023). Hence, cognizance of the significance of structured and critical information acquisition becomes paramount for application users in mitigating confusion and uncertainty.…”

Digital Tourism Recommendation and Route Planning Model Design Based on RippleNet and Improved GA

“…This model combines the latent Dirichlet allocation theme extraction model, word frequency-inverse document frequency weighting, sentiment analysis, and probabilistic hesitant fuzzy algorithms. Jiuzhaigou, China, was analyzed as an example, and the model accurately identified the advantages and disadvantages in scenic area development, which is beneficial for tourists to choose attractions and scenic area improvement [17]. Attractions RM is very critical in solving the information overload problem, and most of the existing RMs are dedicated to improving RM accuracy, which leads to a lack of diversity in recommendation results.…”

“…The model is complex and requires a large amount of computation Tang et al [15] The advantages of integrating non-homogeneous discrete grey models with firefly algorithms Complex model building Sharma et al [16] Integrating the advantages of multiple algorithms, low computational complexity, and ability to handle data noise Not combined with practical tourism needs Luo et al [17] Multi technology integration…”

The Impact of Similarity Fusion based Travel Interest Point Recommendation Algorithm in Youth Users’ Study Tours

“…Meanwhile, fuzzy algorithms were introduced for image mining and model analysis. Small samples were analyzed and the emotions and preferences of tourists were fully considered based on this model [15]. Xu Z constructed a recommendation model using differential privacy theory and clustering methods.…”