Automated Text Categorization Using Support Vector Machine.
James Tin-Yau Kwok · 1998
In this paper, we study the use of support vector machine in text categorization. Unlike other machine learning techniques, it allows easy incorporation of new documents into an existing trained system. Moreover, dimension reduction, which is usually imperative, now becomes optional. Thus, SVM adapts efficiently in dynamic environments that require frequent additions to the document collection. Empirical results on the Reuters-22173 collection are also discussed. 1. Introduction The increasingly widespread use of information services made possible by the Internet and World Wide Web (WWW) has led to the so-called information overloading problem. Today, millions of online documents on every topic are easily accessible via the Internet. As the available information increases, the inability of people to assimilate and profitably utilize such large amounts of information becomes more and more apparent. Developing user-friendly, automatic tools for efficient as well as effective retrieval ...