Deep learning-based logging recommendation using merged code representation

Suin Lee, Youngseok Lee, Chan Gun Lee, Honguk Woo

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

1 Scopus citations

Abstract

When developing a large scale software product, it is essential to share a common set of structural coding guidelines and standards among the project team members. In this paper, we propose MergeLogging, a deep learning-based merged network using various code representations for automated logging decisions or other tasks. MergeLogging archives the enhanced recommendation ability that utilizes orthogonal code features from code representations. Our case study with three open-source project datasets demonstrates that logging accuracy can reach as high as 93%.

Original languageEnglish
Title of host publicationIT Convergence and Security - Proceedings of ICITCS 2020
EditorsHyuncheol Kim, Kuinam J. Kim
PublisherSpringer Science and Business Media Deutschland GmbH
Pages49-53
Number of pages5
ISBN (Print)9789811593536
DOIs
StatePublished - 2021
EventInternational Conference on IT Convergence and Security, ICITCS 2020 - Virtual, Online
Duration: 19 Aug 202021 Aug 2020

Publication series

NameLecture Notes in Electrical Engineering
Volume712
ISSN (Print)1876-1100
ISSN (Electronic)1876-1119

Conference

ConferenceInternational Conference on IT Convergence and Security, ICITCS 2020
CityVirtual, Online
Period19/08/2021/08/20

Keywords

  • Code embedding
  • Deep learning
  • Logging recommendation

Fingerprint

Dive into the research topics of 'Deep learning-based logging recommendation using merged code representation'. Together they form a unique fingerprint.

Cite this