This paper describes an attempt to discover useful knowledge in a collection of over 400,000 reports by call takers on customer's calls received in a PC Help Center. Since each report consists of free text describing the actual dialog with the customer as well as formatted data such as the date and product name, it is very hard to analyze such reports manually.
By integrating natural language processing technology, to extract concepts with their categories and customer's intentions, mining technology, to apply statistical analysis to the concepts, and visualization technology, to provide an overview of the contents of the data collection and to allow interactive analysis of the results, a user can obtain various information such as trends in customers’ claims, and the causes of those trends.
A feasibility study in which the reports were examined by human analysts revealed that the information obtained through this automated analysis is effective in enabling call centers to reduce the number of calls, detect product failures in their early stages, and evaluate the skills of call takers for the purpose of allocation and education
By: Tetsuya Nasukawa, Masayuki Morohashi, Tohru Nagano
Published in: RT0319 in 2002
LIMITED DISTRIBUTION NOTICE:
This Research Report is available. This report has been submitted for publication outside of IBM and will probably be copyrighted if accepted for publication. It has been issued as a Research Report for early dissemination of its contents. In view of the transfer of copyright to the outside publisher, its distribution outside of IBM prior to publication should be limited to peer communications and specific requests. After outside publication, requests should be filled only by reprints or legally obtained copies of the article (e.g., payment of royalties). I have read and understand this notice and am a member of the scientific community outside or inside of IBM seeking a single copy only.
Questions about this service can be mailed to reports@us.ibm.com .