Query expansion terms based on positive and negative association rules

This paper introduces negative association rules to the field of query expansion, and puts forward new models of query expansion; meanwhile, we design an algorithm of query expansion based on positive and negative association rules. By converting the text database to Boolean Vector Matrix, and allotting equitable data storage structure, this algorithm can produce frequent and infrequent feature terms according to the vector inner product, and get positive and negative association rules between terms. Experimental results show that this algorithm can not only expand original query terms quickly and effectively, but also scan the database only once. Meanwhile, it has virtues such as pruning dynamically, without saving mid items, and saving lots of memories, which are important to the research of query expansion in information retrieval.