Classifying bug severity using dictionary based approach

Gujral, Shruti; Sharma, Gitika; Sharma, Sumit; Diksha, .

doi:10.1109/ablaze.2015.7154933

Cited by 21 publications

(6 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Currently researchers, developers, academics, and practitioners need to be aware and consider these bugs [27], [28] to be serious and get more attention [29] even if they need to be issued (Non-Reproducible Bugs), but this requires [30], [19] more profound techniques. Therefore, we will reduce the bugs that have high potential to low levels [31], [2].…”

Section: Methodsmentioning

confidence: 99%

The Performance of Fuzzy Logic How to Fixed The Risk Level of Bug System as Hard-working Quality Software

Pamuji¹

2019

JSC

View full text Add to dashboard Cite

The quality of software production is considered important when testing which is involves several IT Staff such as IT development, operation, end-user. One of the issue was having today is a bug processing where it almost all platforms too difficult to avoid from the bugs and even might be full of the risks. In the main of Our focus is on how to measure and attempt to reduce the number were indicated as bugs from low up to critical levels. Furthermore, we were propose with a method already known as a fuzzy logic approach to measure the severity of the presence of bugs during the testing process. there are 20 thousand even more bugs have been reported and be supposed removed with the fuzzy logic approach with various levels. As The end result is that we have found a gradual 20% reduction in various criteria in the testing process as experimentally. Therefore, fuzzy logic is considered as effective enough to be able to improve existing methods and support to reduce bugs significantly.

show abstract

Section: Methodsmentioning

confidence: 99%

The Performance of Fuzzy Logic How to Fixed The Risk Level of Bug System as Hard-working Quality Software

Pamuji¹

2019

JSC

View full text Add to dashboard Cite

show abstract

“…For this purpose, we want to detect and classify the bugs based on both smells-based and sourced code-based metrics, which is an active research area in software engineering. Some studies on bug classification have been published [10][11][12][13] however, the majority of them are limited to the source code metrics only [14][15][16] which lowers the predictive ability of the preceding bug classification model. This study develops a model, which is based on both source and smell code metrics.…”

Section: 2-problem Statementmentioning

confidence: 99%

Smell-Aware Bug Classification

Khyber,

Ali,

Wahid

et al. 2024

IEEE Access

View full text Add to dashboard Cite

Code smell indicates inadequacies in design and implementation choices. Code smells harm software maintainability including effects on components' bug proneness and code quality has been demonstrated in previous studies. This study aims to investigate the importance of code smell metrics in prediction models for detecting bug-prone code modules. For improvement of the bug prediction model, in this study, smellbased metrics of code have been used. For the training of our model, we employed 14 different open-source projects from the PROMISE repository. Every project file consists of source code as well as smell code metrics and was written in Java. We examined different evaluation metrics such as F1_score, accuracy, precision, recall, the area under the receiver operating characteristic curve, and the area under the precisionrecall curve of the five methods within the version, within the project, and across the projects. We classify the code components as buggy or non-buggy using Naïve Bayes, Random Forest (RF), Support Vector Machine (SVM), Logistic Regression, and k-Nearest Neighbor classifiers. RF and SVM have given better results within the version as well as within the project.

show abstract

“…Eclipse bug report classification is performed by Gujral et al [34], they have achieved 72% precision and 69% accuracy. Moreover, an algorithm that creates dictionary terms is introduced that predicts severity level by selecting a particular component.…”

Section: Related Work a Machine Learning Approachesmentioning

confidence: 99%

Deep Neural Network-Based Severity Prediction of Bug Reports

et al. 2019

View full text Add to dashboard Cite

Software maintenance is an essential phase of software development. Developers employ issue tracking systems to collect bugs for software improvement. Users submit bugs through such issue tracking systems and decide the severity of reported bugs. The severity is an important attribute of a bug that decides how quickly it should be solved. It helps developers to solve important bugs on time. However, manual severity assessment is a tedious job and could be incorrect. To this end, in this paper, we propose a deep neural network-based automatic approach for the severity prediction of bug reports. First, we apply natural language processing techniques for text preprocessing of bug reports. Second, we compute and assign an emotion score for each bug report. Third, we create a vector for each preprocessed bug report. Forth, we pass the constructed vector and the emotion score of each bug report to a deep neural network based classifier for severity prediction. We also evaluate the proposed approach on the history-data of bug reports. The results of cross-product suggest that the proposed approach outperforms the state-of-the-art approaches. On average, it improves the f-measure by 7.90%.

show abstract

Classifying bug severity using dictionary based approach

Cited by 21 publications

References 9 publications

The Performance of Fuzzy Logic How to Fixed The Risk Level of Bug System as Hard-working Quality Software

The Performance of Fuzzy Logic How to Fixed The Risk Level of Bug System as Hard-working Quality Software

Smell-Aware Bug Classification

Deep Neural Network-Based Severity Prediction of Bug Reports

Contact Info

Product

Resources

About