There is a large and continually growing quantity of electronic documents available, which contains essential human and organizations knowledge. An important research endeavor is to study and develop better ways to access this knowledge. Text clustering is a popular approach to automatically organize textual document collections by topics to help users find the information they need. Adaptive Resonance Theory (ART) neural networks possess several interesting properties that make them appealing in the area of text clustering, chiefly for dynamic real-world text collections. Although ART has been used in several research works as a text clustering tool, the quality of the resulting document clusters has not been clearly established. Furthermore, its performance in a dynamic environment---which should be its strength---has never been studied. In this thesis, we present experimental results with binary ART that address these issues. Flat single topic, multi-topic and hierarchical clustering are examined. We also develop a novel clustering quality evaluation approach that allows one to compare text clustering with its supervised counterpart, text categorization.
展开▼
