Query expansion oriented algorithm of positive and negative association rules mining between terms from text database
Yanhong Chen · Computer Engineering and Applications Journal · 2011
Query expansion is one of the most important techniques for improving performance of information retrieval,the key issue of which is how to obtain the expansion terms related to the original query terms.It is an effective method to obtain the expansion terms by association rules mining.A novel algorithm is proposed to mine frequent and infrequent itemsets in text database and to mine both positive and negative association rules between terms in these itemsets,in order to obtain high-quality expansion terms for query expansion.This algorithm uses the framework of support-confidence-correlation to measure association rules,to avoid generating self-contradictory association rules.In the same time,a new pruning strategy is given.It can tremendously enhance the mining efficiency.The experimental results demonstrate that the algorithm is more efficient and more feasible than traditional ones,and can detect and delete those self-contradictory rules and false rules.