%0 Journal Article
	%A Shigeaki Sakurai and  Ryohei Orihara
	%D 2008
	%J International Journal of Computer and Information Engineering
	%B World Academy of Science, Engineering and Technology
	%I Open Science Index 23, 2008
	%T Analysis of Textual Data Based On Multiple 2-Class Classification Models
	%U https://publications.waset.org/pdf/5577
	%V 23
	%X This paper proposes a new method for analyzing textual data. The method deals with items of textual data, where each item is described based on various viewpoints. The method acquires 2- class classification models of the viewpoints by applying an inductive learning method to items with multiple viewpoints. The method infers whether the viewpoints are assigned to the new items or not by using the models. The method extracts expressions from the new items classified into the viewpoints and extracts characteristic expressions corresponding to the viewpoints by comparing the frequency of expressions among the viewpoints. This paper also applies the method to questionnaire data given by guests at a hotel and verifies its effect through numerical experiments.

	%P 3752 - 3757