Automatically Detecting and Organizing Documents into Topic Hierarchies: A Neural Network Based Approach to Bookshelf Creation and Arrangement

Abstract

With the increasing amount of information available in el- ectronic document collections, methods for organizing these collections to allow topic-oriented browsing and orientation gain importance. The SOMLib Digital Library System provides such an organization based on the self-organizing map, a popular neural network model. In this pa- per, we present the GHSOM, which, based on the same concepts, allows an automatic hierarchical decomposition and organization of documents, which very intuitively reflects the organization typically found in (ma- nually organized) conventional libraries. We present a case study based on a 3-month article collection from an Austrian daily newspaper.