عنوان انگلیسی مقاله:
Measuring service quality from unstructured data: A topic modeling application on airline passengers’ online reviews
ترجمه فارسی عنوان مقاله:
اندازه گیری کیفیت خدمات داده های بدون ساختار: یک برنامه مدل سازی موضوع در بررسی های آنلاین مسافران هواپیما
Sciencedirect - Elsevier - Expert Systems With Applications, 116 (2019) 472-486: doi:10:1016/j:eswa:2018:09:037
Nikolaos Korfiatis a , Panagiotis Stamolampros b , ∗, Panos Kourouthanassis c , Vasileios Sagiadinos
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 sys- tems 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 mod- eling 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 ex- plained 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 prob- abilistic 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 dynam- ics 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.
Keywords: Electronic WOM | Unstructured data | Service quality | Correspondence analysis | Structural topic model