Date of Award

Spring 2018

Document Type

Dissertation

Degree Name

Doctor of Philosophy (PhD)

Department

Information Technology & Decision Sciences

Program/Concentration

Business Administration-Information Technology

Committee Director

Wu He

Committee Member

Chuanyi Tang

Committee Member

Ling Li

Committee Member

David D. Selover

Abstract

During the past few decades, social media has provided a number of online tools that allow people to discuss anything freely, with an increase in mobile connectivity. More and more consumers are sharing their opinions online with others. Electronic Word of Mouth (eWOM) is the virtual communication in use; it plays an important role in customers’ buying decisions. Customers can choose to complain or to compliment services or products on their social media platforms, rather than to complete the survey offered by the providers of those services. Compared with the traditional survey, or with the air travel customer report published by U.S. Department of Transportation (DOT) each month, social media offers features that can spread information quickly and broadly. This dissertation offers a novel methodology that, by utilizing emotional sentiment analysis, can help the airline industry to improve its service quality. Longitudinal data, retrieved from Twitter, are collected from twelve U.S.-based airline companies, in order to represent airline companies in different levels and categories. The data covers three consecutive months in Quarter 2 of 2017. Applied alongside the service quality metrics of the airline industry, the benchmark datasets for each metric are created. The purpose of this dissertation is to bridge the gap in traditional methodology for a service quality measurement in the airline industry and to demonstrate the way in which socialized textual data can measure the quality of the service offered by airline service providers. In addition, sentiment analysis is applied, in order to get the sentiment score of each tweet. Emotional lexicons are used to detect the emotion expressed by the tweet in two emotional dimensions: each tweet’s Valence and Arousal are calculated. Once the SERVQUAL model is applied and the keywords to find the corresponding social media data are created for each dimension, the results show that responsiveness, assurance, and reliability are positively correlated to the AQR score that measures the service quality of airline industry. This study also finds that a large amount of negative social media data will negatively affect the AQR score. Finally, this study finds that the interaction of the sentiment score and the arousal score of textual social media data play the important role in predicting the service quality of the airline industry. Finally, an opinion-oriented information system is proposed. In the last, this study provides theory verification of SERVQUAL.

Rights

In Copyright. URI: http://rightsstatements.org/vocab/InC/1.0/ This Item is protected by copyright and/or related rights. You are free to use this Item in any way that is permitted by the copyright and related rights legislation that applies to your use. For other uses you need to obtain permission from the rights-holder(s).

DOI

10.25777/d177-9769

ISBN

9781392058244

ORCID

10.1-3039-/100-0099-80

Download

Share

COinS