Classification of Open-Ended Questionnaires based on Surface Information in Sentence Structure

While the open-ended questionnaire method is a good means to collect free expressions of opinion, the analysis of collected questionnaires is usually done manually, and thus is costly. Furthermore, the results derived from human judgment tend to lack objectivity. Given this background, we explore computational approaches to the automatic classification of collected open-ended questionnaires. This paper reports the results of our preliminary experiments, using "the maximum-entropy model" for questionnaire classification. The results show that our method works well for extracting discriminative linguistic expressions for each response type such as proposal, demand, approval, and opposition, and can produce questionnaire clusters analogous to those produced by humans.