Understanding hidden dimensions in textual reviews on Airbnb: An application of modified latent aspect rating analysis (LARA)

This study provides an innovative research venue for incorporating both textual reviews and numerical ratings into assessment and can assist industry practitioners in identifying review patterns and enhancing user experience.

Abstract

Many customers feel overwhelmed by excessive information provided on peer-review websites (e.g., Yelp). Thus, it is important to generate an effective mechanism to assist customers in identifying the dominant aspects and emotions embedded in textual reviews, and understand the contributions of these aspects and emotions to reviewers' inclusive satisfaction (i.e. overall numerical rating). In the present study the Latent Aspect Rating Analysis (LARA) is modified to achieve this research objective. We identify five aspects; communication, experience, location, product/service, and value. Joy and surprise are the primary emotions shown in textual reviews. This study provides an innovative research venue for incorporating both textual reviews and numerical ratings into assessment. The results also can assist industry practitioners in identifying review patterns and enhancing user experience.