A Self-Organising Map Approach for Clustering of XML Documents

The number of XML documents produced and available on the Internet is steadily increasing. It is thus important to devise automatic procedures to extract useful information from them with little or no intervention by a human operator. In this paper, we investigate the efficacy of an unsupervised learning approach, namely self-organising maps (SOMs), for the automatic clustering of XML documents. Specifically, we consider a relatively large corpus of XML formatted data from the INEX initiative and evaluate it using two different self-organising map models. The first model is the classical SOM model, and it requires the XML documents to be represented by real-valued vectors, obtained using a "bag of words" (or better a "bag of tags") approach. The other model is the SOM for structured data (SOM-SD) approach which is able to cluster structured data, and it is possible to feed the model with tree structured representations of the XML documents, thus explicitly preserving the structural information in the documents. The experimental results show that the SOM model exhibits quite a poor performance on this problem domain which requires the ability to encode structural properties of the data. The SOM-SD model, on the other hand, is able to produce a good clustering and generalization performance.