完全加权正负关联规则算法及其在评教数据中的应用  

All-weighted Positive and Negative Association Rules Algorithm and Its Application in Teaching Evaluation Data

作　　者：周秀梅[1,2] 翁家铭 李石君[2] 

机构地区：[1]南宁地区教育学院数计系,广西崇左532200 [2]武汉大学计算机学院,湖北武汉430072

出　　处：《内蒙古师范大学学报（自然科学汉文版）》2016年第2期242-248,共7页Journal of Inner Mongolia Normal University(Natural Science Edition)

基　　金：国家自然科学基金资助项目(61262028);广西教育厅科研项目(KY2015YB483)

摘　　要：现有的完全加权关联规则挖掘算法没能解决挖掘技术问题,为此提出一种新的完全加权正负关联规则挖掘算法,并探讨了算法在高校评教数据挖掘中的应用.该算法采用新的模式评价标准挖掘有趣的频繁项集和负项集,进而从频繁项集和负项集中挖掘有效的完全加权正负关联规则模式,克服现有挖掘算法的缺陷.以真实的高校评教数据为实验数据测试集,理论和实验结果都表明,该算法比现有完全加权关联规则挖掘算法更有效、合理,具有更高的理论价值和应用前景.The existing mining algorithm of all-weighted association rules cannot resolve the problem of the mining technology. To solve the problem,this paper proposed a novel mining method of all-weighted positive and negative association rules, and discussed its application in college teaching evaluation data as well. By using a new pattern of evaluation standard,interesting frequent itemset and negative itemset were mined, which led to the effective pattern of all-weighted positive and negative association rules. Therefore, this algorithm could supply a gap of the traditional association rules mining. With the real data of college teaching evaluation as test set, the results of the experiments showed that the algorithm proposed in this paper is more effective and more reasonable than the existing mining algorithms of all-weighted positive and negative association rules.

关 键 词：数据挖掘 频繁项集 完全加权关联规则 正负关联规则 评教数据 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]