User-Centered Evaluation of Explainable Artificial Intelligence (XAI): A Systematic Literature Review
Researchers have developed a variety of approaches to evaluate explainable artificial intelligence (XAI) systems using human–computer interaction (HCI) user-centered techniques. This systematic literature review has been conducted to understand how these approaches are used to achieve XAI goals. The...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2024-01-01
|
| Series: | Human Behavior and Emerging Technologies |
| Online Access: | http://dx.doi.org/10.1155/2024/4628855 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849761136409313280 |
|---|---|
| author | Noor Al-Ansari Dena Al-Thani Reem S. Al-Mansoori |
| author_facet | Noor Al-Ansari Dena Al-Thani Reem S. Al-Mansoori |
| author_sort | Noor Al-Ansari |
| collection | DOAJ |
| description | Researchers have developed a variety of approaches to evaluate explainable artificial intelligence (XAI) systems using human–computer interaction (HCI) user-centered techniques. This systematic literature review has been conducted to understand how these approaches are used to achieve XAI goals. The aim of this review is to explore the methods used to evaluate XAI systems in studies involving human subjects. A total of 101 full-text studies were systematically selected and analyzed from a sample of 3414 studies obtained from four renowned databases between 2018 and 2023. The analysis focuses on prominent XAI goals achieved across 10 domains and the machine learning (ML) models utilized to create these XAI systems. The analysis also explores explanation methods and detailed study methodologies used by researchers in previous work. The analysis is concluded by categorizing the challenges experienced by researchers into three types. Exploring the methodologies employed by researchers, the review discusses the benefits and shortcomings of the data collection methods and participant recruitment. In conclusion, this review offers a framework that consists of six pillars that researchers can follow for evaluating user-centered studies in the field of XAI. |
| format | Article |
| id | doaj-art-e0a34e2c4c024e9680f9ebad40029be7 |
| institution | DOAJ |
| issn | 2578-1863 |
| language | English |
| publishDate | 2024-01-01 |
| publisher | Wiley |
| record_format | Article |
| series | Human Behavior and Emerging Technologies |
| spelling | doaj-art-e0a34e2c4c024e9680f9ebad40029be72025-08-20T03:06:06ZengWileyHuman Behavior and Emerging Technologies2578-18632024-01-01202410.1155/2024/4628855User-Centered Evaluation of Explainable Artificial Intelligence (XAI): A Systematic Literature ReviewNoor Al-Ansari0Dena Al-Thani1Reem S. Al-Mansoori2College of Science and EngineeringCollege of Science and EngineeringCollege of Science and EngineeringResearchers have developed a variety of approaches to evaluate explainable artificial intelligence (XAI) systems using human–computer interaction (HCI) user-centered techniques. This systematic literature review has been conducted to understand how these approaches are used to achieve XAI goals. The aim of this review is to explore the methods used to evaluate XAI systems in studies involving human subjects. A total of 101 full-text studies were systematically selected and analyzed from a sample of 3414 studies obtained from four renowned databases between 2018 and 2023. The analysis focuses on prominent XAI goals achieved across 10 domains and the machine learning (ML) models utilized to create these XAI systems. The analysis also explores explanation methods and detailed study methodologies used by researchers in previous work. The analysis is concluded by categorizing the challenges experienced by researchers into three types. Exploring the methodologies employed by researchers, the review discusses the benefits and shortcomings of the data collection methods and participant recruitment. In conclusion, this review offers a framework that consists of six pillars that researchers can follow for evaluating user-centered studies in the field of XAI.http://dx.doi.org/10.1155/2024/4628855 |
| spellingShingle | Noor Al-Ansari Dena Al-Thani Reem S. Al-Mansoori User-Centered Evaluation of Explainable Artificial Intelligence (XAI): A Systematic Literature Review Human Behavior and Emerging Technologies |
| title | User-Centered Evaluation of Explainable Artificial Intelligence (XAI): A Systematic Literature Review |
| title_full | User-Centered Evaluation of Explainable Artificial Intelligence (XAI): A Systematic Literature Review |
| title_fullStr | User-Centered Evaluation of Explainable Artificial Intelligence (XAI): A Systematic Literature Review |
| title_full_unstemmed | User-Centered Evaluation of Explainable Artificial Intelligence (XAI): A Systematic Literature Review |
| title_short | User-Centered Evaluation of Explainable Artificial Intelligence (XAI): A Systematic Literature Review |
| title_sort | user centered evaluation of explainable artificial intelligence xai a systematic literature review |
| url | http://dx.doi.org/10.1155/2024/4628855 |
| work_keys_str_mv | AT nooralansari usercenteredevaluationofexplainableartificialintelligencexaiasystematicliteraturereview AT denaalthani usercenteredevaluationofexplainableartificialintelligencexaiasystematicliteraturereview AT reemsalmansoori usercenteredevaluationofexplainableartificialintelligencexaiasystematicliteraturereview |