Semiautomated Identification and Classification of Customer Complaints

Abstract

This paper examines the feasibility of extracting useful information from customer comments using a Naïve 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 Naïve 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.

Application of a Machine Learning–Based Decision Support Tool to Improve an Injury Surveillance System Workflow

“…20 Bayesian DSS have been found to be effective in various injury surveillance, health care, and other applications, including (1) learning of motor vehicle accident categories, 21 (2) coding of occupational injury cases, 18 (3) automatic indexing of documents, 22 (4) providing interactive decision support related to print quality to customers, 23 and (5) classification and identification of customer complaints. 24 Similar to the NB model, the LR model also outputs the likelihood of correctness of prediction, and thus, both these models were used to develop the classifier for QISU.…”

Complaint management model of manufacturing products using text mining and potential failure identification

“…Upon receiving those complaints, the company can classify to know what things are complained. According to Choe et al (2013), a complaint can be classified as transaction-related, product-related, customer service-or support-related and customer outreach and marketing-related. Linder et al (2014) stated that product-related complaints can be used for improving product and process quality of the company.…”

Pre-trained language models as knowledge bases for Automotive Complaint Analysis

“…in terms of potential security risks identified and mentioned by customers. However, the structured use of this data is an open problem in industry, despite numerous investigations with advanced NLP methods (Choe et al, 2013;Lee et al, 2015;Akella et al, 2017;Liang et al, 2017;Joung et al, 2019). Handling this fuzzy data and satisfying the demand for detailed information extraction in an intelligent manner remains challenging.…”

“…With these methods it is impossible to automatically identify newly emerging, possibly security-relevant, risks. The lack of labeled training data as well as imbalanced data is a hurdle in the development of NLP models in industrial customer feedback analysis (Choe et al, 2013;Akella et al, 2017). Furthermore, it is relevant for product manufacturers to be able to identify implied connections in customer feedback.…”