Automatic Document Classification

Abstract

A computer cannot determine the subject content of a document the way the librarians do. Automatic classification is concerned with the procedures and systems that can make comparison between terms used. Using the computer to provide automatic indexes can only be considered for the automatic production of title indexes or the keyword enhanced index. Classificatory techniques, in fact, can be used for improving the efficiency of these title indexes. This paper attempts to trace solutions to the problems, such as truncation, stemming, etc. Automatic keyword classification is only an attempt. The use of automatically constructed classification is still a subject for investigation.

http://dx.doi.org/10.14429/dbit.19.3.3486