摘要
针对从数据集中的正负关联规则挖掘问题,提出一种基于双阈值Apriori算法和非频繁项集的挖掘方法。首先,对通过逆文档频率(IDF)对语料库中的项(项集)进行加权,筛选出前N%的项集;然后,通过提出的双支持度阈值Apriori算法来提取频繁项集和非频繁项集,以此降低非频繁项集的数量;最后,通过置信度和升降度阈值的判断,分别从频繁项集和非频繁项集中挖掘正负关联规则。其中,创新性地利用了非频繁项集来挖掘正负关联规则。在一个医学文本数据集上的实验结果表明,提出的方法能够有效地挖掘出正负关联规则,且能够大大降低项集和规则数量。
For the issues that mining positive and negative association rules from the dataset,this paper proposed a mining method based on double threshold Apriori algorithm and infrequent itemsets. Firstly,it weighted the items in the corpus by the inverse document frequency（ IDF） to filter out the top N% of the itemsets. Then,it extracted the frequent itemsets and the nonfrequent itemsets through the proposed double support threshold Apriori algorithm,to reduce the number of infrequent itemsets.Finally,it excavated the positive and negative association rules respectively from the frequent itemsets and the infrequent itemsets through the judgment of the confidence level and lifting. Among them,it innovative used of infrequent itemsets to mining positive and negative association rules. The experimental results on a medical text dataset show that the proposed method can effectively mine the positive and negative association rules and can greatly reduce the number of itemsets and rules.
作者
阮梦黎
吴磊
Ruan Mengli;Wu Lei(School of Information Engineering,Shandong Management University,Jinan 250357,China;School of Information Science ＆ Engineering,Shandong Normal University,Jinan 250358,China)
出处
《计算机应用研究》
CSCD
北大核心
2018年第12期3579-3583,共5页
Application Research of Computers
基金
国家自然科学基金资助项目(61602287)
山东省社会科学规划研究项目(17CQXJ11)
山东省高等学校科技计划资助项目(J16LN70)
关键词
正负关联规则挖掘
双支持度阈值
APRIORI算法
非频繁项集
IDF加权
positive and negative association rule mining
double support threshold
Apriori algorithm
infrequent item-sets
IDF weighting
