Explainable AI for SE: Challenges and future directions

Chakkrit Tantithamthavorn; Jurgen Cito; Hadi Hemmati; Satish Chandra

doi:10.1109/MS.2023.3246686

Explainable AI for SE: Challenges and future directions

Chakkrit Tantithamthavorn, Jurgen Cito, Hadi Hemmati, Satish Chandra

Department of Software Systems & Cybersecurity

Research output: Contribution to journal › Editorial › Other

18 Citations (Scopus)

Abstract

In recent years, artificial intelligence/machine learning (AI/ML) have been widely used in software engineering (SE) to improve developer productivity, software quality, and decision making. This includes well-known tools for code completion (for example, GitHub’s Copilot) but also code search; automated task recommendation; automated developer recommendation; automated defect/vulnerability/malware prediction, detection, localization, and repair; and many other purposes.

Original language	English
Pages (from-to)	29-33
Number of pages	5
Journal	IEEE Software
Volume	40
Issue number	3
DOIs	https://doi.org/10.1109/MS.2023.3246686
Publication status	Published - May 2023

Access to Document

10.1109/MS.2023.3246686

470563218-oaFinal published version, 1.6 MB

Cite this

@article{57de4d87683d447c89c1f643bc7f4836,

title = "Explainable AI for SE: Challenges and future directions",

abstract = "In recent years, artificial intelligence/machine learning (AI/ML) have been widely used in software engineering (SE) to improve developer productivity, software quality, and decision making. This includes well-known tools for code completion (for example, GitHub{\textquoteright}s Copilot) but also code search; automated task recommendation; automated developer recommendation; automated defect/vulnerability/malware prediction, detection, localization, and repair; and many other purposes.",

author = "Chakkrit Tantithamthavorn and Jurgen Cito and Hadi Hemmati and Satish Chandra",

year = "2023",

month = may,

doi = "10.1109/MS.2023.3246686",

language = "English",

volume = "40",

pages = "29--33",

journal = "IEEE Software",

issn = "0740-7459",

publisher = "IEEE, Institute of Electrical and Electronics Engineers",

number = "3",

}

TY - JOUR

T1 - Explainable AI for SE

T2 - Challenges and future directions

AU - Tantithamthavorn, Chakkrit

AU - Cito, Jurgen

AU - Hemmati, Hadi

AU - Chandra, Satish

PY - 2023/5

Y1 - 2023/5

N2 - In recent years, artificial intelligence/machine learning (AI/ML) have been widely used in software engineering (SE) to improve developer productivity, software quality, and decision making. This includes well-known tools for code completion (for example, GitHub’s Copilot) but also code search; automated task recommendation; automated developer recommendation; automated defect/vulnerability/malware prediction, detection, localization, and repair; and many other purposes.

AB - In recent years, artificial intelligence/machine learning (AI/ML) have been widely used in software engineering (SE) to improve developer productivity, software quality, and decision making. This includes well-known tools for code completion (for example, GitHub’s Copilot) but also code search; automated task recommendation; automated developer recommendation; automated defect/vulnerability/malware prediction, detection, localization, and repair; and many other purposes.

UR - https://www.scopus.com/pages/publications/85156104914

U2 - 10.1109/MS.2023.3246686

DO - 10.1109/MS.2023.3246686

M3 - Editorial

AN - SCOPUS:85156104914

SN - 0740-7459

VL - 40

SP - 29

EP - 33

JO - IEEE Software

JF - IEEE Software

IS - 3

ER -

Explainable AI for SE: Challenges and future directions

Abstract

Access to Document

Other files and links

Cite this