Exploiting Confusion Matrices for Relevance Ranking of Text Documents
Arpana Rawal, M. K. Kowar, Sanjay Sharma · 2008
Current research on Ontologies has shown that 5 they facilitate the information retrieval, query-based interaction and knowledge management of text document resources. The authors report the implementation of the machine-generated Ontologies on the huge-text corpora that can be assumed to a part of mechanized Digital Libraries for extracting conceptual features by computing the measure of semantic closeness, upon the selectively chosen highly focused terms. This angle of visualizing text literature searching and ranking has been ignored so far in much existing work. In the present communication, a two-stage approach is implied, where a confusion matrix : a measure of true class of test instances against the predicted classes is innovatively used to derive a fuzzy preference relation matrix - the most suitably thought metric to proceed for the task of text document ranking. The authors visualize the promising results from an experimental set up laid upon a sample text corpus that served as a driving lexicon for constructing relevant concept spaces.