2016/04/04 by Emanuel Lacić, Dominik Kowald, Lacic, Emanuel +3
Business, Management and Accounting · Computer Science · Economics, Econometrics and Finance · Social Sciences · #Aviation Industry Analysis and Trends #Consumer Market Behavior and Pricing #Data Stream Mining Techniques #Digital Marketing and Social Media #FOS: Computer and information sciences #Information Retrieval (cs.IR) #Transportation Planning and Optimization
paper · pdf · doi:10.48550/arxiv.1604.00942
openalex publication_date 2016/04/04 · openalex created_date 2022/08/29 · openalex updated_date 2026/07/28
Air travel is one of the most frequently used means of transportation in our\nevery-day life. Thus, it is not surprising that an increasing number of\ntravelers share their experiences with airlines and airports in form of online\nreviews on the Web. In this work, we thrive to explain and uncover the features\nof airline reviews that contribute most to traveler satisfaction. To that end,\nwe examine reviews crawled from the Skytrax air travel review portal. Skytrax\nprovides four review categories to review airports, lounges, airlines and\nseats. Each review category consists of several five-star ratings as well as\nfree-text review content. In this paper, we conducted a comprehensive feature\nstudy and we find that not only five-star rating information such as airport\nqueuing time and lounge comfort highly correlate with traveler satisfaction but\nalso textual features in the form of the inferred review text sentiment. Based\non our findings, we created classifiers to predict traveler satisfaction using\nthe best performing rating features. Our results reveal that given our\nmethodology, traveler satisfaction can be predicted with high accuracy.\nAdditionally, we find that training a model on the sentiment of the review text\nprovides a competitive alternative when no five star rating information is\navailable. We believe that our work is of interest for researchers in the area\nof modeling and predicting user satisfaction based on available review data on\nthe Web.\n