ECAI 2004 Conference Paper

[full paper]

AntTree: A web document clustering using artificials ants

Azzag Hanene, Christianne Guinot, Gilles Venturini

We present in this work a new algorithm (called AntTree) for document hierarchical clustering and automatic generation of portals sites. This model is inspired from the self-assembling behaviour observed in real ants where ants progressively get attached to an existing support and successively to others attached ants. We have simulated the way ants build complex structures by connecting themselves to each others. The artificial ants that we have defined will similarly build a tree. Each ant represents one document. The way ants move and build this tree depends on the similarity between the documents. In this paper we have shown how this behaviour can be used to build a hierarchical tree-structured partitioning of a set of documents. We have tested AntTree on a set of web pages extracted from internet and we have successfully compared our results presented as a series of HTML files with hyperlinks, to those obtained by the AHC (Ascending Hierarchical Clustering), we have shown that our algorithm obtains competitive results in term of classification error, the number of classes “found” and computational time, those results are extremely encouraging and the main perspective of this work is to keep on studying this promising model.

Keywords: Text Mining, Hierarchical clustering, Autonomous Agents, Artificials ants, Portals sites, Web document

Citation: Azzag Hanene, Christianne Guinot, Gilles Venturini: AntTree: A web document clustering using artificials ants. In R.López de Mántaras and L.Saitta (eds.): ECAI2004, Proceedings of the 16th European Conference on Artificial Intelligence, IOS Press, Amsterdam, 2004, pp.480-484.