File(s) under permanent embargo
Lessons learned from using a deep tree-based model for software defect prediction in practice
conference contribution
posted on 2019-01-01, 00:00 authored by H K Dam, Trang Pham, S W Ng, Truyen TranTruyen Tran, John Grundy, A Ghose, T Kim, C J Kim© 2019 IEEE. Defects are common in software systems and cause many problems for software users. Different methods have been developed to make early prediction about the most likely defective modules in large codebases. Most focus on designing features (e.g. complexity metrics) that correlate with potentially defective code. Those approaches however do not sufficiently capture the syntax and multiple levels of semantics of source code, a potentially important capability for building accurate prediction models. In this paper, we report on our experience of deploying a new deep learning tree-based defect prediction model in practice. This model is built upon the tree-structured Long Short Term Memory network which directly matches with the Abstract Syntax Tree representation of source code. We discuss a number of lessons learned from developing the model and evaluating it on two datasets, one from open source projects contributed by our industry partner Samsung and the other from the public PROMISE repository.
History
Event
Mining Software Repositories. Conference (2019 : 16th : Montreal, Quebec)Pagination
46 - 57Publisher
IEEELocation
Montreal, QuebecPlace of publication
Piscataway, N.J.Publisher DOI
Start date
2019-05-25End date
2019-05-31ISSN
2160-1852eISSN
2160-1860ISBN-13
9781728134123Language
engPublication classification
E1 Full written paper - refereedTitle of proceedings
MSR 2019 : Proceedings of the 16th IEEE/ACM International Conference on Mining Software RepositoriesUsage metrics
Categories
No categories selectedKeywords
Licence
Exports
RefWorks
BibTeX
Ref. manager
Endnote
DataCite
NLM
DC