Similarity Model and Term Association for Document Categorization

This paper addresses similarity model and term association for similarity-based document categorization. Both Euclidean distance– and cosine-based similarity models are widely used for measures of document similarity in information retrieval and document categorization community. These two similarity models are based on the assumption that term vectors are orthogonal. Term associations are ignored in such similarity models. In fact, the assumption above is not true. In the context of document categorization, we analyze the properties of term-document space, termcategory space and category-document space. Then, without the assumption of term independence, we propose a new mathematical model to estimate the association between terms. Different from other models of term relationship, here we make best use of existing category membership represented by corpus as more as possible, and the objective is to improve categorization performance. By introducing association between terms, we take into account term associations for calculating document similarity and define a -similarity model of documents. Experiments have been done with kNN classifier over Reuters-5178 corpus. The empirical results show that utilization of term association can improve the effectiveness of categorization system and -similarity model outperforms than ones without considering term association.