Evaluating airline service quality through a comprehensive text-mining and multi-criteria decision-making analysis

Service quality is of paramount importance for the long-term sustainability of the airline industry, which is characterized by intense competition. However, previous research in this field has frequently been limited by shortcomings in sample size, efficiency, and dependability. This study addresses these deficiencies by introducing refined insights and establishing a comprehensive yet highly elucidative ranking framework. Initially, we employ Latent Semantic Analysis (LSA) to distill principal themes and sentiments from online reviews of 80 airlines. Subsequently, we employ the SentiWordNet lexicon and the TextBlob package for sentiment analysis based on the aforementioned reviews. Following this, we construct a hierarchical structure using the computation of compromise solutions, employing an integrated Technique for Order Preference by Similarity to Ideal Solution, vis-à-vis Kriterijumska Optimizacija I Kompromisno Resenje-Adversarial Interpretive Structural Model (TOPSIS-VIKOR-AISM) methodology. Finally, the ranking of airlines from best to worst based on perceptions gained from online reviews provides an immediate visualization solution. This study not only assists consumers in making informed decisions but also provides airlines with insights that can be used to enhance their service offerings. The study presents novel insights into the assessment of service quality, with potential applicability to the airline industry and beyond.