Topic Modeling of Online Accommodation Reviews via Latent Dirichlet Allocation

Sustainability

SeulKi Lee¹  Youngseok Sim¹  Jaemun Byun¹  Kiattipoom Kiatkawsin¹  Ian Sutherland¹ 

[1] Department of Hospitality and Tourism Management, Tourism Industry Data Analytics Lab (TIDAL), Sejong University, Seoul 05006;

关键词: topic modeling;    latent dirichlet allocation;    tourism 4.0;    online travel agency;    online review;    text analytics;    improve customer satisfaction;    inductive approach;    dimensions of interest;    era of big data;   

DOI  :  10.3390/su12051821

来源: DOAJ

【 摘 要 】

There is a lot of attention given to the determinants of guest satisfaction and consumer behavior in the tourism literature. While much extant literature uses a deductive approach for identifying guest satisfaction dimensions, we apply an inductive approach by utilizing large unstructured text data of 104,161 online reviews of Korean accommodation customers to frame which topics of interest guests find important. Using latent Dirichlet allocation, a generative, Bayesian, hierarchical statistical model, we extract and validate topics of interest in the dataset. The results corroborate extant literature in that dimensions, such as location and service quality, are important. However, we extend existing dimensions of importance by more precisely distinguishing aspects of location and service quality. Furthermore, by comparing the characteristics of the accommodations in terms of metropolitan versus rural and the type of accommodation, we reveal differences in topics of importance between different characteristics of the accommodations. Specifically, we find a higher importance for points of competition and points of uniqueness among the accommodation characteristics. This has implications for how managers can improve customer satisfaction and how researchers can more precisely measure customer satisfaction in the hospitality industry.

【 授权许可】

Unknown