DeepSoft: a vision for a deep model of software

Hoa Khanh Dam, Truyen Tran, John Grundy, Aditya Ghose

Research output: Chapter in Book/Report/Conference proceedingConference PaperResearchpeer-review

7 Citations (Scopus)

Abstract

Although software analytics has experienced rapid growth as a research area, it has not yet reached its full poten-tial for wide industrial adoption. Most of the existing work in software analytics still relies heavily on costly manual feature engineering processes, and they mainly address the traditional classification problems, as opposed to predicting future events. We present a vision for DeepSoft, an end-to-end generic framework for modeling software and its de-velopment process to predict future risks and recommend interventions. DeepSoft, partly inspired by human memory, is built upon the powerful deep learning-based Long Short Term Memory architecture that is capable of learning long-term temporal dependencies that occur in software evolu-tion. Such deep learned patterns of software can be used to address a range of challenging problems such as code and task recommendation and prediction. DeepSoft provides a new approach for research into modeling of source code, risk prediction and mitigation, developer modeling, and auto-matically generating code patches from bug reports.

Original languageEnglish
Title of host publicationProceedings of the 2016 24th ACM SIGSOFT International Symposium on Foundations of Software Engineering
EditorsThomas Zimmermann, Jane Cleland-Huang, Zhendong Su
Place of PublicationNew York NY USA
PublisherAssociation for Computing Machinery (ACM)
Pages944-947
Number of pages4
ISBN (Electronic)9781450342186
DOIs
Publication statusPublished - 2016
Externally publishedYes
EventACM SIGSOFT International Symposium on Foundations of Software Engineering 2016 - Seattle, United States of America
Duration: 13 Nov 201618 Nov 2016
Conference number: 24th
https://www.cs.ucdavis.edu/fse2016/

Conference

ConferenceACM SIGSOFT International Symposium on Foundations of Software Engineering 2016
Abbreviated titleFSE 2016
CountryUnited States of America
CitySeattle
Period13/11/1618/11/16
Internet address

Keywords

  • Mining Software Repositories
  • Software Analytics

Cite this