Measuring service quality from unstructured data: A topic modeling application on airline passengers’ online reviews

Abstract

Service quality is a multi-dimensional construct which is not accurately measured by aspects deriving from numerical ratings and their associated weights. Extant literature in the expert and intelligent systems examines this issue by relying mainly on such constrained information sets. In this study, we utilize online reviews to show the information gains from the consideration of factors identified from topic modeling of unstructured data which provide a flexible extension to numerical scores to understand customer satisfaction and subsequently service quality. When numerical and textual features are combined, the explained variation in overall satisfaction improves significantly. We further present how such information can be of value for firms for corporate strategy decision-making when incorporated in an expert system that acts as a tool to perform market analysis and assess their competitive performance. We apply our methodology on airline passengers' online reviews using Structural Topic Models (STM), a recent probabilistic extension to Latent Dirichlet Allocation (LDA) that allows the incorporation of document level covariates. This innovation allows us to capture dominant drivers of satisfaction along with their dynamics and interdependencies. Results unveil the orthogonality of the low-cost aspect of airline competition when all other service quality dimensions are considered, thus explaining the success of low-cost carriers in the airline market.

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

“…Although all these topic modeling tools also can extract latent topics from the text, these tools have different focuses and require additional variables to be added in the application. For example, the emphasis of using STM is to examine the impact of pre-defined covariates on the changes of topic prevalence (Korfiatis et al, 2019). As for DTM, it is often applied to identify changes in customer perception toward certain products over time (Ha et al, 2017).…”

Harnessing the “wisdom of employees” from online reviews

“…Probabilistic topic modeling methods are suitable for the analysis of review text (Korfiatis, et al, 2019). Among several alternative specifications we choose the structural topic model -STM (Roberts et al, 2014), that has the advantage of allowing the incorporation of review metadata such as employee status, or industry on the review-topic proportion, relaxing the restrictive assumption of exchangeability, where all employees are considered equally likely to reflect on any topic.…”

Airline service quality and economic factors: An ARDL approach on US airlines

“…Hitherto, literature has studied airline service quality from different perspectives. The vast majority of studies propose metrics to capture accurately service quality (Chou, Liu, Huang, Yih, & Han, 2011;Higgins, Lawphongpanich, Mahoney, & Yin, 2008;Korfiatis, Stamolampros, Kourouthanassis, & Sagiadinos, 2019;Liou & Tzeng, 2007) and focuses on the service quality factors that passengers value more (Babbar & Koufteros, 2008;Gilbert & Wong, 2003;Pakdil & Aydın, 2007) usually through SERVQUAL or its modifications. Other studies discuss differences of service quality among carriers or differences in customer expectations from different service providers such as low cost versus legacy carriers (David Mc A, 2013;Wittman, 2014).…”