Reduction of Redundant Rules in Association Rule Mining-Based Bug Assignment

Abstract

Bug triaging is a process to decide what to do with newly coming bug reports. In this paper, we have mined association rules for the prediction of bug assignee of a newly reported bug using diff erent bug attributes, namely, severity, priority, component and operating system. To deal with the problem of large data sets, we have taken subsets of data set by dividing the large data set using Kmeans clustering algorithm. We have used an Apriori algorithm in MATLAB to generate association rules. We have extracted the association rules for top 5 assignees in each cluster. The proposed method has been empirically validated on 14,696 bug reports of Mozilla open source software project, namely, Seamonkey, Firefox and Bugzilla. In our approach, we observe that taking on these attributes (severity, priority, component and operating system) as antecedents, essential rules are more than redundant rules, whereas in [M. Sharma and V. B. Singh, Clustering-based association rule mining for bug assignee prediction, Int. J. Business Intell. Data Mining 11(2) (2017) 130-150.] essential rules are less than redundant rules in every cluster. The proposed method provides an improvement over the existing tech-niques for bug assignment problem.

Automating Bug Triage: Unleashing the Power of Machine Learning and Natural Language Processing

“…[22] conducted a Comparative Study, revealing Information Retrieval-based techniques outperforming Machine Learning techniques. [23] employed Association Rule Mining, obtaining higher confidence values. [24] explored Ensemble Learning with a recall of up to 96%.…”

An Extended Survey Concerning the Significance of Artificial Intelligence and Machine Learning Techniques for Bug Triage and Management

“…Proper machine learning-based models [2] [3] are frequently used in this respect (Softmax classifier, Support Vector Machine, Multinomial Naive Bayes, K-Nearest Neighbors, J48, Random Forests, Artificial Neural Networks), along with clustering [4] and association rule mining [5]. SBT is regarded as a multiclass, single-label classification problem [6], which considers the software developer as a class. Thus, it is immediately discernible that the proper classification techniques are frequently used relative to machine learning-based bug triaging techniques.…”

A novel and improved developer rank algorithm for bug assignment

“…Three products of Mozilla namely Thunderbird, AddOnSDK and Bugzilla are used for result validation and the reported result is secured 81% accuracy for top-three recommended developers. The extended version of this paper is also presented by Sharma et al (2017) which were evaluated on large number of bug reports, i.e., 14,696 of Mozilla open source projects. Banitaan and Alenezi (2013) presented a social network-based bug triaging approach called DECOBA that indicates that collaborative efforts of the developers for bug fixing.…”