Method for atypical opinion extraction from answers in open-ended questions

This paper presents a method for atypical opinion extraction from answers to open-ended questions supplied by users of a mobile game content when they unsubscribe from the service. The proposed system excludes typical opinions and extracts only atypical opinions. To cope with incomplete syntax of texts due to the input by mobile phone, the system treats the opinions as the sets of keywords. The combination of words are established beforehand in a typical word database. Based on the ratio of typical word combinations in sentences of an opinion, the system classifies the opinion typical or atypical. When typical word combinations are sought in an opinion, the system considers the word order and the distance of difference between the positions of words to exclude unnecessary combinations. Furthermore, when an opinion includes meanings the system divides the opinion into phrases at each typical word combination. With an experiment, the extraction accuracy of the proposed system was confirmed.