Feature Comparison for Automatic Bug Report Classification

Luaphol, Bancha; Srikudkao, Boonchoo; Kachai, Tontrakant; Srikanjanapert, Natthakit; Polpinij, Jantima; Bheganan, Poramin

doi:10.1007/978-3-030-19861-9_7

Cited by 8 publications

(7 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, it was unsurprising that unigram+CamelCase as features returned more satisfactory results for assembling dependent bug reports. Then, our reason may be similar to [10], [13], [33]- [35].…”

Section: Evaluation Of the Proposed Methodsmentioning

confidence: 83%

“…Bug report features (or words) used here are unigram and CamelCase. Unigram means a single word, while CamelCase [10], [13], [33]- [35] (also referred to as Snakecase or Compound words) is to write a word by using two words or abbreviations together to yield a new meaning with no punctuation and intervening spaces. Some CamelCase words often begin with a capital letter or use the capital letter in the middle of words.…”

Section: Bug Report Pre-processingmentioning

confidence: 99%

“…Some examples of CamelCase are "browser_views" and "UrlBar". Before using CamelCase words as features, these words are split into single words [10], [13], [33]- [35]. For examples, CamelCase words such as "browser_views" and "UrlBar" can be split as "browser", "views", "Url", and "Bar", respectively.…”

Section: Bug Report Pre-processingmentioning

confidence: 99%

“…Unigram and CamelCase are popularly used in bug report studies because a unigram is simple to extract from a bug report, while CamelCase can indicate the specificity of the software [10], [12], [13], [15]- [17], [19], [33]- [35], [49], [50]. Two different types of features are used to obtain the most satisfactory results, namely unigram and unigram+CamelCase.…”

Section: Bug Report Pre-processingmentioning

confidence: 99%

See 3 more Smart Citations

Automatic dependent bug reports assembly for bug tracking systems by threshold-based similarity

Luaphol

Polpinij²,

Kaneampornpan³

2021

IJEECS

View full text Add to dashboard Cite

<p>Bug reports contain essential information for fixing problems that occur in software. Many studies have proposed methods for automatic analysis of bug reports. One such task could affect the completion of software bug fixing, known as “bug dependency”. Although this problem was mentioned by many researches, most of them discussed about the related bugs but not really dealt with dependency issue in bug reports. One possible solution used for addressing this issue is to assemble all relevant/dependent bug reports together before analysis of the next processing stages. This study presents a method of assembling dependent bug reports. The main mechanism is called “threshold-based similarity analysis”, and the three similarity techniques of cosine similarity (CS) multi aspect TF (MATF), and BM25 are compared with feedback, precision and likelihood value. As the BM25 with the threshold as 0.5 gives the best results, it was used to compare with the state of the art method. The results show that our method increases precision and likelihood values by 12% and 12.4% respectively. Therefore, our results can be used to encourage developers to recognize all dependent bugs in the same problem domain.</p>

show abstract

Section: Evaluation Of the Proposed Methodsmentioning

confidence: 83%

Section: Bug Report Pre-processingmentioning

confidence: 99%

Section: Bug Report Pre-processingmentioning

confidence: 99%

Section: Bug Report Pre-processingmentioning

confidence: 99%

See 2 more Smart Citations

Automatic dependent bug reports assembly for bug tracking systems by threshold-based similarity

Luaphol

Polpinij²,

Kaneampornpan³

2021

IJEECS

View full text Add to dashboard Cite

show abstract

“…Bug tickets are labelled as BUG while other issue tickets are labelled as NBUG. Many works [9], [10], [11], [12], [13], [14] [12] aim to discover the most efficient features for binary bug report classification. This study compares seven ways of processing textual information using sub-sequences of words: unigrams, bigrams, camel case, unigrams and bigrams, unigrams and camel case, bigrams and camel case, and all kinds of sub-sequences together.…”

Section: Existing Binary Bug Classification Approachesmentioning

confidence: 99%

Bug or not bug? That is the question

Perez¹,

Jean²,

Urtado³

et al. 2021

Preprint

View full text Add to dashboard Cite

Nowadays, development teams often rely on tools such as Jira or Bugzilla to manage backlogs of issues to be solved to develop or maintain software. Although they relate to many different concerns (e.g., bug fixing, new feature development, architecture refactoring), few means are proposed to identify and classify these different kinds of issues, except for non mandatory labels that can be manually associated to them. This may lead to a lack of issue classification or to issue misclassification that may impact automatic issue management (planning, assignment) or issue-derived metrics. Automatic issue classification thus is a relevant topic for assisting backlog management. This paper proposes a binary classification solution for discriminating bug from non bug issues. This solution combines natural language processing (TF-IDF) and classification (multi-layer perceptron) techniques, selected after comparing commonly used solutions to classify issues. Moreover, hyper-parameters of the neural network are optimized using a genetic algorithm. The obtained results, as compared to existing works on a commonly used benchmark, show significant improvements on the F1 measure for all datasets.

show abstract