Knowledge discovery of service satisfaction based on text analysis of critical incident dialogues and clustering methods

Charles Trappey, Hsin Ying Wu*, Kuan Liang Liu, Feng Teng Lin

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

3 Scopus citations

Abstract

Text mining of consumer's dialogues regarding their service experiences provides a direct and unbiased feedback to service providers. This research proposes an analysis process to analyze unstructured input from consumer dialogues. The goal is to apply the critical incident and text mining methods to discover factors that contribute to customer satisfaction and dissatisfaction. The critical incident method is used to construct an open-ended questionnaire to collect customer's positive and negative opinions toward the service provided. Valid and reliable text mining techniques are used to cluster significant text to help analyze incidents that customers care about. A case study of consumers riding the Kaohsiung Mass Rapid Transit System (KMRT) was cased to evaluate the proposed analysis process. Based on dialogues collected from the open-ended questionnaires, the analysis process extracts key phrases related to consumer's best and worst service experiences, creates significant dialogue clusters, and derives meaningful trends, baselines, and interpretations of consumer satisfaction and dissatisfaction. The results of this case study can be used as a basis for building more complete analytical methods to understand consumer experiences and provide strategic feedback for service providers.

Original languageEnglish
Title of host publicationProceedings - 2013 IEEE 10th International Conference on e-Business Engineering, ICEBE 2013
PublisherIEEE Computer Society
Pages265-270
Number of pages6
ISBN (Print)9780769551111
DOIs
StatePublished - 1 Jan 2013
Event2013 IEEE 10th International Conference on e-Business Engineering, ICEBE 2013 - Coventry, United Kingdom
Duration: 11 Sep 201313 Sep 2013

Publication series

NameProceedings - 2013 IEEE 10th International Conference on e-Business Engineering, ICEBE 2013

Conference

Conference2013 IEEE 10th International Conference on e-Business Engineering, ICEBE 2013
CountryUnited Kingdom
CityCoventry
Period11/09/1313/09/13

Keywords

  • CKIP
  • Cluster analysis
  • Critical incident techniques
  • Customer satisfaction
  • KMRT
  • Text mining

Fingerprint Dive into the research topics of 'Knowledge discovery of service satisfaction based on text analysis of critical incident dialogues and clustering methods'. Together they form a unique fingerprint.

Cite this