Towards an Improvement of Bug Report Summarization Using Two-Layer Semantic Information

Abstract

Bug report summarization has been explored in past research to help developers comprehend important information for bug resolution process. As text mining technology advances, many summarization approaches have been proposed to provide substantial summaries on bug reports. In this paper, we propose an enhanced summarization approach called TSM by first extending a semantic model used in AUSUM with the anthropogenic and procedural information in bug reports and then integrating the extended semantic model with the shallow textual information used in BRC. We have conducted experiments with a dataset of realistic software projects. Compared with the baseline approaches BRC and AUSUM, TSM demonstrates the enhanced performance in achieving relative improvements of 34.3% and 7.4% in the F1 measure, respectively. The experimental results show that TSM can effectively improve the performance.

Comparative Study of Bug Report Summarization Techniques

“…• The model with too-much complex-ity is giving the results similar to other approaches. Towards an Improvement of Bug Report Summarization Using Two-Layer Semantic Information [YANG et al (2018)]…”

“…Most popular approach used by bug report researchers is Feature-Based Approach where the researchers like [Rastkar et al (2010)], [ Rastkar et al (2014)], [ Taware & Shinde (2015)] used the domain-based features to extract the important sentences from the bug report data. Apart from feature-based approach, unsupervised approach is also one of the other famous approach used by researchers like [Kumarasamy Mani et al (2012)], [Lotufo et al (2015)], [YANG et al (2018)]. Along with the feature-based and unsupervised approaches the researchers have also used machine-based classifier approach and the support vector machines [Lotufo et al(2015)], [ Rastkar et al (2010)], [Rastkar et al (2014)], [YANG et al (2018)], [ He et al (2017)].…”

“…Apart from feature-based approach, unsupervised approach is also one of the other famous approach used by researchers like [Kumarasamy Mani et al (2012)], [Lotufo et al (2015)], [YANG et al (2018)]. Along with the feature-based and unsupervised approaches the researchers have also used machine-based classifier approach and the support vector machines [Lotufo et al(2015)], [ Rastkar et al (2010)], [Rastkar et al (2014)], [YANG et al (2018)], [ He et al (2017)]. Topic Modelling techniques like Latent Dirichlet Allocation(LDA) is also used in bug reports to extract the important topics [Nagwani & Verma (2016)].…”

“…They also discussed the use of cloud computing to reduce the time to summarize for neural-based networks. Towards an Improvement of Bug Report Summarization Using Two-Layer Semantic Information [YANG et al (2018)] As in the bug reports, the diversity and natural language is there and the work mainly relies on the effectiveness of classification of sentences. It is important to analyze and improve the classification system to improve the summaries.…”

CaPBug-A Framework for Automatic Bug Categorization and Prioritization Using NLP and Machine Learning Algorithms

“…Software testing and maintenance are the most critical phases of software development. Bug reports play a vital role in these stages of development activities [1], [2]. A bug report is generated by the software quality assurance team while testing software modules.…”