SemCluster: a semi-supervised clustering tool for crowdsourced test reports with deep image understanding

Du, Mingzhe; Yu, Shuling; Fang, Chunrong; Li, Tongyu; Zhang, Heyuan; Chen, Zhenyu

doi:10.1145/3540250.3558933

Cited by 5 publications

(10 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Table V lists the papers with their focus area. These results lead us to deduce that the crowdsourcing methods in general software engineering crowdsourcing are suitable for mobile crowdsourcing, except for mobile testing methods highlighted by [40]- [44]. V. CONCLUSION This literature review examines and studies the latest papers in crowdsourced software engineering to find the current trends and directions of the research literature.…”

Section: Resultsmentioning

confidence: 93%

“…Can general crowdsourced software engineering methods be used in mobile crowdsourcing? Mobile development comes with its own set of problems, especially in software testing [40]- [44] describe these issues. In this review, there are ten papers that focus exclusively on mobile crowdsourcing, specifically mobile testing.…”

Section: Resultsmentioning

confidence: 99%

“…2) Test report clustering and prioritization: The authors of [40] assert that an issue of the previous research papers dealing with the clustering of test reports is that the papers do not take into account the semantic connection between the screenshots and text in the analyzed test reports, which results in suboptimal results, especially in the deduplication of test reports. Therefore, This paper proposes a method using semi-supervised clustering using deep image understanding to analyze crowdsourced mobile application test reports.…”

Section: Software Verification and Validationmentioning

confidence: 99%

“…[42] state that in addition to the large number of test reports produced by crowdsourcing that needs inspecting, one specific issue of mobile application test reports is that they have more screenshots than text descriptions of the tests. In addition to this paper, [40], [41], [43], [44] deal with these issues as well. To solve the issues of the number of reports and screenshots, the authors of [42] propose a novel method to understand text and images to cluster test reports.…”

Section: Software Verification and Validationmentioning

confidence: 99%

“…DivClass combines diversity and classification strategies to order the reports for inspection. A feature of this method is that it handles duplicate test reports similar to the method proposed in [40], [42]- [44] in which they use natural language processing to analyze the test reports in one of their method steps. The next step in [44] is to build a similarity matrix using an asymmetric computation strategy.…”

Section: Liu Et Al Inmentioning

confidence: 99%

See 4 more Smart Citations

A Review of Trending Crowdsourcing Topics in Software Engineering Highlighting Mobile Crowdsourcing and AI Utilization

Alghasham¹,

Alzakan²,

Al-Hagery³

2023

IJACSA

View full text Add to dashboard Cite

Today's modern technologies and requirements make the utilization of crowdsourcing more viable and applicable. It is one of the problem-solving models that can be used in various domains to reduce costs and time. It is also an excellent way to find new and different ideas and solutions. This paper studies the use of crowdsourcing in software engineering and reveals adequate details to highlight its significance. A few recent literature reviews have been published to address specific topics or study general attributes of papers in crowdsourced software engineering. This paper, however, explores all recent publications related to software and crowdsourcing to find the trends and highlight mobile and AI usage in software crowdsourcing. The findings of this paper show that most research papers are in the areas of software management and software verification and validation. The results also reveal that machine learning and data mining techniques are predominant in software management crowdsourcing and software verification and validation. Furthermore, this study shows that the methods and techniques used in general crowdsourcing apply to mobile crowdsourcing except in mobile testing, where there is a need for clustering and prioritization of test reports.

show abstract

Section: Resultsmentioning

confidence: 93%

Section: Resultsmentioning

confidence: 99%

Section: Software Verification and Validationmentioning

confidence: 99%

Section: Software Verification and Validationmentioning

confidence: 99%

Section: Liu Et Al Inmentioning

confidence: 99%

See 3 more Smart Citations

A Review of Trending Crowdsourcing Topics in Software Engineering Highlighting Mobile Crowdsourcing and AI Utilization

Alghasham¹,

Alzakan²,

Al-Hagery³

2023

IJACSA

View full text Add to dashboard Cite

show abstract

Crowdsourced bug report severity prediction based on text and image understanding via heterogeneous graph convolutional networks

Wu,

Lin,

Liu

et al. 2024

J Software Evolu Process

View full text Add to dashboard Cite

In the process of crowdsourced testing, massive bug reports are submitted. Among them, the severity level of the bug report is an important indicator for traigers of crowdsourced platforms to arrange the order of reports efficiently so that developers can prioritize high‐severity defects. A lot of work has been devoted to the study of automatically assigning severity levels to a large number of bug reports in crowdsourcing test systems. The research objects of these works are standard bug reports, focusing on the text part of the report, using various feature engineering methods and classification techniques. However, while achieving good performance, these methods still need to overcome two challenges: no consideration of image information in mobile testing and discontinuous semantic information of words in bug reports. In this paper, we propose a new method of severity prediction by using heterogeneous graph convolutional networks with screenshots (SPHGCN‐S), which combines text features and screenshots information to understand the report more comprehensively. In addition, our approach applies the heterogeneous graph convolutional network (HGCN) architecture, which can capture the global word information to alleviate the semantic problem of word discontinuity and underlying relations between reports. We conduct a comprehensive study to compare seven commonly adopted bug report severity prediction methods with our approach. The experimental results show that our approach SPHGCN‐S can improve severity prediction performance and effectively predict reports with high severity.

show abstract

Semantic GUI Scene Learning and Video Alignment for Detecting Duplicate Video-based Bug Reports

Yan,

Cooper,

Chaparro

et al. 2024

Proceedings of the IEEE/ACM 46th International Conference on Software Engineering

View full text Add to dashboard Cite

Video-based bug reports are increasingly being used to document bugs for programs centered around a graphical user interface (GUI). However, developing automated techniques to manage video-based reports is challenging as it requires identifying and understanding often nuanced visual patterns that capture key information about a reported bug. In this paper, we aim to overcome these challenges by advancing the bug report management task of duplicate detection for video-based reports. To this end, we introduce a new approach, called Janus, that adapts the scene-learning capabilities of vision transformers to capture subtle visual and textual patterns that manifest on app UI screens -which is key to differentiating between similar screens for accurate duplicate report detection. Janus also makes use of a video alignment technique capable of adaptive weighting of video frames to account for typical bug manifestation patterns. In a comprehensive evaluation on a benchmark containing 7,290 duplicate detection tasks derived from 270 video-based bug reports from 90 Android app bugs, the best configuration of our approach achieves an overall mRR/mAP of 89.8%/84.7%, and for the large majority of duplicate detection tasks, outperforms prior work by ≈9% to a statistically significant degree. Finally, we qualitatively illustrate how the scene-learning capabilities provided by Janus benefits its performance. CCS CONCEPTS• Software and its engineering → Software evolution.

show abstract

SemCluster: a semi-supervised clustering tool for crowdsourced test reports with deep image understanding

Cited by 5 publications

References 8 publications

A Review of Trending Crowdsourcing Topics in Software Engineering Highlighting Mobile Crowdsourcing and AI Utilization

A Review of Trending Crowdsourcing Topics in Software Engineering Highlighting Mobile Crowdsourcing and AI Utilization

Crowdsourced bug report severity prediction based on text and image understanding via heterogeneous graph convolutional networks

Semantic GUI Scene Learning and Video Alignment for Detecting Duplicate Video-based Bug Reports

Contact Info

Product

Resources

About