Towards Understanding the Impacts of Textual Dissimilarity on Duplicate Bug Report Detection

Jahan, Sigma; Rahman, Mohammad Masudur

doi:10.1109/saner56733.2023.00013

Cited by 3 publications

(1 citation statement)

References 55 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This algorithm is based on the idea of creating a separate hidden Markov model for each cluster, which allows determining which cluster the given stack belongs to. The stack can be represented as a discrete sequence of states or function calls (10). To determine the number of observable states (11), all unique frames of stacks for all reports in the cluster should be found.…”

Section: Report An Errormentioning

confidence: 99%

Deduplication of error reports in software malfunction: Algorithms for comparing call stacks

Pavlenko,

Kuliabko

2023

bcstu

View full text Add to dashboard Cite

In the software industry, the standard recognises automatic fault monitoring systems as mandatory for implementation. Considering the constant development of technologies and the high complexity of programmes, the importance of optimising processes for detecting and eliminating errors becomes a relevant task due to the need for reliability and stability of software. The purpose of this study is to conduct a detailed analysis of existing deduplication algorithms for reports from automatic systems collecting information about software failures. Among the algorithms considered were: the longest common subsequence method, Levenshtein distance, deep learning methods, Siamese neural networks, and hidden Markov models. The results obtained indicate a great potential for optimising processes of error detection and elimination in software. The developed comprehensive approach to the analysis and detection of duplicates in call stacks in failure reports allows for effectively addressing issues. The deep learning methods and hidden Markov models have demonstrated their effectiveness and feasibility for real-world applications. Effective methods for comparing key parameters of reports are identified, which contributes to the identification and grouping of recurring errors. The use of call stack comparison algorithms has proven critical for accurately identifying similar error cases in products with large audiences and high parallelism conditions. Siamese neural networks and the Scream Tracker 3 Module algorithm are used to determine the similarity of call stacks, including the application of recurrent neural networks (long short-term memory, bidirectional long short-term memory). Optimisation of report processing and clustering particularly enhances the speed and efficiency of responding to new failure cases, allowing developers to improve system stability and focus on high-priority issues. The study is useful for software developers, software development companies, system administrators, research groups, algorithm and tool development companies, cybersecurity professionals, and educational institutions

show abstract

Section: Report An Errormentioning

confidence: 99%