Semiautomated Identification and Classification of Customer Complaints

This paper examines the feasibility of extracting useful information from customer comments using a Naive Bayes classifier. This was done for a database, obtained from a large Korean mobile telephone service provider, of 533 customer calls to call centers in 2009. After eliminating calls not containing customer complaints or comments, the remaining 383 comments were classified by an expert panel into four domains and 27 complaint categories. The four domains were Transaction-related 189 comments, 49%, Product-related 120 comments, 31%, Customer Service or Support-related 38 comments, 10% and Customer Outreach and Marketing-related 36 comments, 9%. The comments were then randomly assigned to either a training set 257 cases, 67% or test set 126 cases, 33%. The training set was used to develop a Naive Bayes classifier that correctly predicted the domain 75% of the time and the specific subcategory 51% of the time for the test set. Prediction accuracy was strongly related to prediction strength for both sets of predictions, suggesting that simple filtering strategies where difficult to understand comments are flagged for expert review and easy comments are automatically classified are both technically feasible and likely to be practically valuable. Several strong predictors were also identified that corresponded to categories more detailed than those originally assigned. © 2012 Wiley Periodicals, Inc.

[1]  Francisco Tamayo Enríquez,et al.  TQM and QFD: exploiting a customer complaint management system , 2005 .

[2]  Mary Jo Bitner,et al.  Self-Service Technologies: Understanding Customer Satisfaction with Technology-Based Service Encounters , 2000 .

[3]  High Quality and Low Quality Internet Service Encounters , 2000 .

[4]  Christina Sanes.  Mining the gold in customer complaints: Complaints are hidden treasure , 1993 .

[5]  Jan P. Allebach,et al.  Query translation-based cross-language print defect diagnosis based on the fuzzy Bayesian model , 2011, J. Intell. Manuf..

[6]  Jillian C. Sweeney,et al.  Critical service quality encounters on the Web: an exploratory study , 2004 .

[7]  M Lehto,et al.  Bayesian methods: a useful tool for classifying injury narratives into cause groups , 2009, Injury Prevention.

[8]  M R Lehto,et al.  Machine learning of motor vehicle accident categories from narrative data. , 1996, Methods of information in medicine.

[9]  J. C. Flanagan.  Psychological Bulletin THE CRITICAL INCIDENT TECHNIQUE , 2022 .

[10]  Gavriel Salvendy,et al.  Critical purchasing incidents in e-business , 2008, Behav. Inf. Technol..

[11]  Chulwoo Kim,et al.  Evaluating and Improving a Self-Help Technical Support Web Site: Use of Focus Group Interviews , 2006, Int. J. Hum. Comput. Interact..

[12]  Schubert Foo,et al.  An integrated help support for customer services over the World Wide Web: a case study , 2000 .

[13]  T. Lam,et al.  Customer complaint behaviour towards hotel restaurant services , 2003 .

[14]  Lukas P. Forbes,et al.  Typologies of e‐commerce retail failures and recovery strategies , 2005 .

[15]  Christian Homburg,et al.  How Organizational Complaint Handling Drives Customer Loyalty: An Analysis of the Mechanistic and the Organic Approach , 2005 .

[16]  K. Vohs,et al.  Case Western Reserve University , 1990 .

[17]  Mark R Lehto,et al.  Computerized coding of injury narrative data from the National Health Interview Survey. , 2004, Accident; analysis and prevention.

[18]  Sugani Leman,et al.  Interactive decision support system to predict print quality , 2003, Ergonomics.

[19]  Mary Jo Bitner,et al.  The Service Encounter: Diagnosing Favorable and Unfavorable Incidents: , 1990 .

[20]  Larry Lockshin,et al.  Service problems and recovery strategies: an examination of the critical incident technique in a business‐to‐business market , 1998 .

[21]  M. Butts,et al.  Are Bad Experiences Stronger than Good Ones in Mentoring Relationships? Evidence from the Protege and Mentor Perspective. , 2010 .