The Self-Organizing Map (SOM) is an unsupervised neural network algorithm that projects high- dimensional data onto a two-dimensional map. The projection preserves the topology of the data so that similar data items will be mapped to nearby locations on the map. Despite the popular use of the algorithm for clustering and information visualisation, a system has been lacking that combines the fast execution of the algorithm with powerful visualisation of the maps and effective tools for their interactive analysis. Powerful methods for interactive exploration and search from collections of free-form textual documents are needed to manage the ever-increasing flood of digital information. In this article we present a method, SOM, for automatic organization of full-text document collections using the self-organizing map (SOM) algorithm. The document collection is ordered onto a map in an unsupervised manner utilizing statistical information of short word contexts. The resulting ordered map where similar documents lie near each other thus presents a general view of the document space. With the aid of a suitable (SVG) interface, documents in interesting areas of the map can be browsed. Information Visualization with Self-Organizing Maps