Researcher bias: The use of machine learning in software defect prediction
- Submitting institution
-
Brunel University London
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 006-94651-8735
- Type
- D - Journal article
- DOI
-
10.1109/TSE.2014.2322358
- Title of journal
- Ieee Transactions On Software Engineering
- Article number
- -
- First page
- 603
- Volume
- 40
- Issue
- 6
- ISSN
- 0098-5589
- Open access status
- Out of scope for open access requirements
- Month of publication
- June
- Year of publication
- 2014
- URL
-
http://bura.brunel.ac.uk/handle/2438/8784
- 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)
-
2 - Software, Systems & Security (SSS)
- Citation count
- 132
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This paper, based on a large-scale meta-analysis, identifies deficiencies with previous research practices in software defect prediction, and makes recommendations for computational experiments. It is the 3rd most cited paper (out of 433) among all TSE (the top software engineering journal) papers published since 2014 (1st among non-survey papers) and the 44th most downloaded paper of all time. This paper has influenced many groups e.g., Queen's (Ca), Waterloo, Cisco Systems, Wuhan/Nanjing, N Carolina State, Nat Inst Tech Raipur, Salerno, UCL, Keele, Wroclaw etc. Implications are discussed in the definitive software engineering handbook by Kitchenham et al (2015).
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -
