Text analytics based severity prediction of software bugs for apache projects

Abstract

Severity i.e impact, extent and effect on software is a decisive attribute which decides how instantly the bug should be fixed. Predicting the severity of software bugs is important to improve the bug triaging and resolution process. To reduce the effort and time required in manual assessment of severity of newly reported bugs, many techniques and methods are used in past researches. To help software developers to utilize their resources efficiently, this study evaluates a number of machine learning techniques for predicting the severity of software bugs at system and component level. The techniques are evaluated on thirteen apache projects automatically extracted using the Bug Report Collection System tool. Severity is predicted based on the most frequent terms extracted from the summary of bugs using text mining. Performance metrics such as precision, recall and accuracy are used to interpret the results obtained from various techniques. The result of the study advocates that Boosting (an ensemble learner) technique outperforms other machine learning techniques such as Bayesian learners, decision tree, support vector machine applied in previous researches.

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

“…These resources consider bug location information, term weighting in TF-IDF, and time metadata concerning the TF-IDF presentation. Additionally, software bug triaging uses both text mining, which is presented in articles [16], [17], [18], [19], and also text similarity models, which are described in articles [20], [20], [21], [22], [23], [24], [25].…”

Extractive summarization using concept‐space and keyword phrase

“…Stemming – it converts any words to its base form. Suffixes such as ed, ly, ing are removed from the words (Kaur & Jindal, 2019).…”

An empirical study of non-reproducible bugs

“…A plethora of research efforts has been made in the literature on software debugging practices to ensure proper handling of software bugs. The majority of these efforts focus on bug report summarization (Rastkar et al 2014), severity (Pushpalatha and Mrunalini 2019;Kaur and Jindal 2019;Yang et al 2019) and priority (Tian et al 2015) prediction, duplicate detection (Lazar et al 2014;Sureka and Jalote 2010), bug report assignment (Shokripour et al 2015;Xia et al 2017;Goyal and Sardana 2017b), reopened bug prediction (Shihab et al 2013), bug fix time prediction (Marks et al 2011;Akbarinasaji et al 2017), etc. All of these past studies have considered only fixed bug reports for their experimental evaluation.…”