Homogeneous Ants for Web Document Similarity Modeling and Categorization

Abstract

The self-organizing and autonomous behavior of social insects such as ants presents an interesting and powerful metaphor for applications in the retrieval and management of large and fast growing amount of online information. The explosive growth of web documents has increasingly made more difficult and costly the manual task of organizing the documents into meaningful categories by human experts. Hence, it is desirable that some degree of automation be incorporated into the classification process to enable better scalability and prevent human classifiers from being overwhelmed by the deluge of information. This paper presents a preliminary investigation of applying a homogeneous multi-agent clustering system based on the self-organization behavior of the ants to the high-dimensional problem of web document categorization. A description of the text processing needed to obtain significant document features is included. The system will be evaluated on multi-class online English documents obtained from a popularly used search engine.