Automatically Identifying Code Features for Software Defect Prediction: Using AST N-grams
- Submitting institution
-
University of Central Lancashire
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 24433
- Type
- D - Journal article
- DOI
-
10.1016/j.infsof.2018.10.001
- Title of journal
- Information and Software Technology
- Article number
- -
- First page
- 142
- Volume
- 106
- Issue
- -
- ISSN
- 0950-5849
- Open access status
- Compliant
- Month of publication
- October
- Year of publication
- 2018
- URL
-
-
- Supplementary information
-
-
- Request cross-referral to
- -
- Output has been delayed by COVID-19
- No
- COVID-19 affected output statement
- -
- Forensic science
- No
- Criminology
- No
- Interdisciplinary
- No
- Number of additional authors
-
2
- Research group(s)
-
-
- Citation count
- 6
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This paper, published in a high-quality venue, showed the significance of AST N-grams in relation to software defect prediction (finding faults) in Java software code. Software failures are known to cost millions of dollars to companies and economies, highlighting the importance of this work. The paper showed that AST N-grams were more effective than conventional approaches, a key feature of this work is the use of opensource systems and commercial software. An ACM Transactions on SE in 2020 by Rabab, Capur and Sodhi acknowledged this work as being the current state of the art in this field.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -