LCBPA: An Enhanced Deep Neural Network-Oriented Bug Prioritization and Assignment Technique Using Content-Based Filtering

Abstract

Software maintenance is an important phase of a development life cycle that needs to be essentially performed in order to avoid the software failure. To systematically handle the bugs (defects), the software development organization develops a bug report that demonstrates the vulnerabilities from the software under test. However, manually handling the bug reports is a laborious, tedious, and time-consuming task. Moreover, the bug repository receives large numbers of bug reports on daily basis, which demands to timely fix the found and received bugs. Motivated by this, current work proposes an automated bug prioritization and assignment technique, called LCBPA (Long short-term memory, Content-based filtering for Bug Prioritization and Assignment). To perform the bug prioritization, we employed Long Short-Term Memory (LSTM) to predict the priority of the bug report. In contrast, for bug assignment, we used contentbased filtering, where the prioritized bug reports are automatically assigned to the developers based on their previous knowledge. The performance of the proposed bug prioritization model is determined by comparing with the state-of-the-art bug prioritization techniques using precision, recall and f1-score. Similarly, the effectiveness of the bug assignment model is evaluated by defining various case scenarios. The results show that the proposed LCBPA technique outperforms the current state-of-the-art bug prioritization techniques (with a 22% increase in F1-score), and also efficiently handles the bug assignment problem compared to the existing bug assignment techniques.

Deep Bug Reports Processing (DBRP): A Systematic Literature Review

“…However, unstructured features of bug reports in combination with textual content and developer history were also considered. A recent paper (Tahir, Khan and Ali, 2021) proposed bug prioritization and assignment approach based on LSTM and content filtering. Herein, LSTM was utilized to capture the important representations of bug reports and match them with appropriate priority value.…”

“…However, recent papers proposed approaches to utilize categorical features of bug reports. Tahir et al (2021) used product and component features to improve bug report triage. While the in (Rodrigues et al, 2020) proposed priority and developer comments to detect duplicates accurately.…”

Intelligent System to Detect Software Defects in Autonomous Cars

“…Different programming languages are not explored, such as Java. [11] 2021 Bug prediction and assignment using LSTM and Contentbased filtering, respectively.…”

“…Researchers worldwide presented their works on the prioritization of different bugs based on their impact and timing. For example, Tahir et al [11] proposed an automated model to prioritize the bugs in software components and assign bug reports to the specialized developer. It is based on previous knowledge and past experiences.…”

“…They preferred the LSTM model to prioritize defect reports and then used a content-based filtering technique for assignment purposes. This model has been pre-processed with the help of the Natural Language Processing (NLP) method and uses Senti4SD [11] for classifying bug reports based on different emotions.…”