ALLEVIATING SEARCH UNCERTAINTY THROUGH CONCEPT ASSOCIATIONS - AUTOMATIC-INDEXING, COOCCURRENCE ANALYSIS, AND PARALLEL COMPUTING

In this article, we report research on an algorithmic approach to alle viating search uncertainty in a large information space. Grounded on o bject filtering, automatic indexing, and co-occurrence analysis, we pe rformed a large-scale experiment using a parallel supercomputer (SGI P ower Challenge) to analyze 400,000+ abstracts in an INSPEC computer en gineering collection. Two system-generated thesauri, one based on a co mbined object filtering and automatic indexing method, and the other b ased on automatic indexing only, were compared with the human-generate d INSPEC subject thesaurus. Our user evaluation revealed that the syst em-generated thesauri were better than the INSPEC thesaurus in concept recall, but in concept precision the 3 thesauri were comparable. Our analysis also revealed that the terms suggested by the 3 thesauri were complementary and could be used to significantly increase ''variety'' in search terms and thereby reduce search uncertainty.