Semantic Methods In Software Defect Prediction Techniques

Date

2024-1-1

Author

Işıkoğlu, Şükrücan Taylan

Metadata

Show full item record

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

Item Usage Stats

134
views

88
downloads

Cite This

The traditional methods in software defect prediction use software metrics that are collected from the source code. However these methods have an important shortcoming: it is possible that two source code segments, where one is buggy and one is not, have the same software metrics. Software metrics are not descriptive enough to discern defective code. Recently semantic methods have been explored. These methods use the source code directly and extract semantic information using methods that involve deep learning. This research presents a survey of the use of semantic methods in software defect prediction.

Subject Keywords

software defect prediction, semantic, semantic methods, deep learning

URI

https://hdl.handle.net/11511/108245

Collections

Graduate School of Informatics, Term Project