Home > Research > Publications & Outputs > Systematic Review of XAI Tools for AI-HCI Research

Electronic data

View graph of relations

Systematic Review of XAI Tools for AI-HCI Research

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSNConference contribution/Paperpeer-review

Forthcoming

Standard

Systematic Review of XAI Tools for AI-HCI Research. / Alaqsam, Ahmad; Sas, Corina.
37th International BCS Human-Computer Interaction Conference. British Computer Society, 2024.

Research output: Contribution in Book/Report/Proceedings - With ISBN/ISSNConference contribution/Paperpeer-review

Harvard

Alaqsam, A & Sas, C 2024, Systematic Review of XAI Tools for AI-HCI Research. in 37th International BCS Human-Computer Interaction Conference. British Computer Society, British HCI Conference, Preston, United Kingdom, 15/07/24.

APA

Alaqsam, A., & Sas, C. (in press). Systematic Review of XAI Tools for AI-HCI Research. In 37th International BCS Human-Computer Interaction Conference British Computer Society.

Vancouver

Alaqsam A, Sas C. Systematic Review of XAI Tools for AI-HCI Research. In 37th International BCS Human-Computer Interaction Conference. British Computer Society. 2024

Author

Alaqsam, Ahmad ; Sas, Corina. / Systematic Review of XAI Tools for AI-HCI Research. 37th International BCS Human-Computer Interaction Conference. British Computer Society, 2024.

Bibtex

@inproceedings{7cfff6ab38ac405aa033fb3d46b69c52,
title = "Systematic Review of XAI Tools for AI-HCI Research",
abstract = "The explainability of machine learning black-box models is key for designing and adopting AI technologies by end users. XAI tools such as SHAP or LIME have been purposely developed to support such explainability but their exploration in the HCI community has been limited. This paper reports a systematic review of 142 papers targeting design, use or evaluation of XAI tools with the aim to investigate their different types, users, application domains, input and output data sets, and their user interfaces. Findings indicate a broad range of XAI tools but extensive use of a few, a prevalence of AI experts as users rather than evaluators of these tools. We discuss our findings arguing for the need to move beyond the design of novel XAI tools towards increasing their use and comparative evaluation. We also argue for the need for HCI-grounded user interface design for XAI tools and advance an initial design space for AI-HCI research integrating AI affordances with the application domains of XAI tools mapped to key HCI research areas. ",
author = "Ahmad Alaqsam and Corina Sas",
year = "2024",
month = jul,
day = "12",
language = "English",
booktitle = "37th International BCS Human-Computer Interaction Conference",
publisher = "British Computer Society",
note = "British HCI Conference : BHCI 2024 ; Conference date: 15-07-2024 Through 17-07-2024",
url = "https://bcshci.org/",

}

RIS

TY - GEN

T1 - Systematic Review of XAI Tools for AI-HCI Research

AU - Alaqsam, Ahmad

AU - Sas, Corina

PY - 2024/7/12

Y1 - 2024/7/12

N2 - The explainability of machine learning black-box models is key for designing and adopting AI technologies by end users. XAI tools such as SHAP or LIME have been purposely developed to support such explainability but their exploration in the HCI community has been limited. This paper reports a systematic review of 142 papers targeting design, use or evaluation of XAI tools with the aim to investigate their different types, users, application domains, input and output data sets, and their user interfaces. Findings indicate a broad range of XAI tools but extensive use of a few, a prevalence of AI experts as users rather than evaluators of these tools. We discuss our findings arguing for the need to move beyond the design of novel XAI tools towards increasing their use and comparative evaluation. We also argue for the need for HCI-grounded user interface design for XAI tools and advance an initial design space for AI-HCI research integrating AI affordances with the application domains of XAI tools mapped to key HCI research areas.

AB - The explainability of machine learning black-box models is key for designing and adopting AI technologies by end users. XAI tools such as SHAP or LIME have been purposely developed to support such explainability but their exploration in the HCI community has been limited. This paper reports a systematic review of 142 papers targeting design, use or evaluation of XAI tools with the aim to investigate their different types, users, application domains, input and output data sets, and their user interfaces. Findings indicate a broad range of XAI tools but extensive use of a few, a prevalence of AI experts as users rather than evaluators of these tools. We discuss our findings arguing for the need to move beyond the design of novel XAI tools towards increasing their use and comparative evaluation. We also argue for the need for HCI-grounded user interface design for XAI tools and advance an initial design space for AI-HCI research integrating AI affordances with the application domains of XAI tools mapped to key HCI research areas.

M3 - Conference contribution/Paper

BT - 37th International BCS Human-Computer Interaction Conference

PB - British Computer Society

T2 - British HCI Conference

Y2 - 15 July 2024 through 17 July 2024

ER -