Researcher bias : The use of machine learning in software defect prediction
- Submitting institution
-
The University of Lancaster
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 250153180
- Type
- D - Journal article
- DOI
-
10.1109/TSE.2014.2322358
- Title of journal
- IEEE Transactions on Software Engineering
- Article number
- 6824804
- 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
-
-
- 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)
-
H - Software Engineering
- Citation count
- 132
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This paper was highly controversial being the first to highlight potentially unreliable defect prediction results stemming from researcher bias. Subsequent to publication this paper generated extensive discussion amongst the defect prediction community (also published in IEEE Transactions in Software Engineering). Arguably, the paper made a significant impact on improving the approaches used by researchers in defect prediction studies (many of the 218 studies citing this paper present state-of-the-art practices motivated by the guidelines reported by the paper). The findings of this paper resulted in a number of invitations to give conference keynotes, e.g. at KKIO2017 and PROMISE2018.
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -
