Exploring changes in guest preferences for Airbnb accommodation with different levels of sharing and prices: Using structural topic model.

Introduction: Online reviews have become an important source of information for investigating customers' consumption experiences in academic studies. In the context of sharing economy-based accommodation, various studies have been conducted to investigate the user experience of Airbnb by analyzing online reviews; however, most previous Airbnb studies had focused on analyzing the user experience of Airbnb at a holistic level without distinguishing the accommodation attributes of Airbnb. Therefore, this article aimed to investigate how the preferences revealed by Airbnb users in online reviews vary across Airbnb listings with different levels of sharing and price ranges.

Exploring Sources of Satisfaction and Dissatisfaction in Airbnb Accommodation Using Unsupervised and Supervised Topic Modeling.

This study aims to examine key attributes affecting Airbnb users' satisfaction and dissatisfaction through the analysis of online reviews. A corpus that comprises 59,766 Airbnb reviews form 27,980 listings located in 12 different cities is analyzed by using both Latent Dirichlet Allocation (LDA) and supervised LDA (sLDA) approach. Unlike previous LDA based Airbnb studies, this study examines positive and negative Airbnb reviews separately, and results reveal the heterogeneity of satisfaction and dissatisfaction attributes in Airbnb accommodation.