Predictive self-organizing networks for text categorization

Abstract. This paper introduces a class of predictive self-organizing neural networks known as Adaptive Resonance Associative Map (ARAM) for classication of free-text documents. Whereas most statistical ap-proaches to text categorization derive classication knowledge based on training examples alone, ARAM performs supervised learning and in-tegrates user-dened classication knowledge in the form of IF-THEN rules. Through our experiments on the Reuters-21578 news database, we showed that ARAM performed reasonably well in mining categorization knowledge from sparse and high dimensional document feature space. In addition, ARAM predictive accuracy and learning eciency can be im-proved by incorporating a set of rules derived from the Reuters category description. The impact of rule insertion is most signicant for categories with a small number of relevant documents.