Issue No. 05 - September/October (2002 vol. 17)
<p>Surveys are an important part of marketing and customer relationship management, and open answers (answers to open questions) in particular could contain valuable information and provide an important basis for making business decisions. The authors have developed a text mining system that provides a new way of analyzing open answers in questionnaire data. The product can perform the following two functions: accurate extraction of characteristics for individual analysis targets and accurate extraction of the relationships among characteristics of analysis targets. In this article, they describe how their text mining system works. It has already been put to use by several large corporations in Japan, providing answers to questions about brand images, company images, complaints about products, comments written on home pages, business reports, and help desk records. In this it has been found to be useful in forming a basis for effective business decisions.</p>
text mining, survey, questionnaire data, open question, classification rules, association rules, correspondence analysis, data mining
H. Li and K. Yamanishi, "Mining Open Answers in Questionnaire Data," in IEEE Intelligent Systems, vol. 17, no. , pp. 58-63, 2002.