Effective Implementation of Basic Operations for Information Retrieval

In the article we describe the approach to parallel implementation of elementary operations for textual data categorization. In the experiments we evaluate parallel computations of similarity matrices and k-means algorithm. The test datasets have been prepared as graphs created from Wikipedia articles related with links. W also present the approach to computing pairs of eigenvectors and eigenvalues for visualizations of the datasets. The implemented basic operations: computing similarity matrix, data clustering and spectral analysis have been used in our system for visualization of the Wikipedia categories on SOM as well as in a system for categorization search results in Wikipedia.