Knowledge discovery of customer satisfaction and dissatisfaction using ontology-based text analysis of critical incident dialogues

Ontology based systems have long been recognized by researchers as the starting point for automated text analysis (or text mining) of consumer dialogues. Therefore, this research creates an ontology schema for consumer complaint dialogues related to mass rapid transportation systems. Based on the complaint ontology, the critical incident technique is used to construct an open-ended customer questionnaire to collect the positive and negative text dialogues of passengers describing their transportation experiences. Several valid and reliable methods have been developed to cluster significant text using the frequency of key words. An example would be the use of keyword frequency (KF) analysis and the formation of clusters based on KF to study patents and technology trends. The intention of this research is to use these methods to automatically text mine consumer dialogues, create significant dialogue clusters, and, from these clusters, derive meaningful trends, baselines, and interpretations of consumer satisfaction and dissatisfaction with a mass transit system in a major metropolitan city.