Enhancing AI Explainability Through the EXACT Framework: A User-Centric Approach
The increasing adoption of Artificial Intelligence (AI) in several industries has created a demand for user-centered explanations that align with how users think and understand concepts. This paper presents EXACT (EXplainable AI with Cognitive Theories), a novel framework that combines cognitive the...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/11021617/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850121456722116608 |
|---|---|
| author | Sara S. Alhasan Reem A. Alnanih |
| author_facet | Sara S. Alhasan Reem A. Alnanih |
| author_sort | Sara S. Alhasan |
| collection | DOAJ |
| description | The increasing adoption of Artificial Intelligence (AI) in several industries has created a demand for user-centered explanations that align with how users think and understand concepts. This paper presents EXACT (EXplainable AI with Cognitive Theories), a novel framework that combines cognitive theories that explain how people think and understand with cognitive functions, focusing on perception, memory and language abilities, to improve users’ comprehension of and engagement with artificial intelligence technologies. By aligning cognitive functions with the design principles of Human-Computer Interaction (HCI), which promote user-centered intuitive systems. the framework addresses challenges related to making AI understandable to users with various levels of cognitive abilities. As a proof-of-concept, a self-diagnosis tool was created to demonstrate the framework’s effectiveness. Then, 60 participants were divided into a control group and an experimental group. Participants completed six tasks designed to evaluate their perception, memory, and language-related cognitive functions. The experimental group outperformed the control group across all tasks, demonstrating significantly improved performance. Subjective metrics also supported these findings: the experimental group reported higher levels of understanding (4.60 vs. 2.87), confidence (4.67 vs. 3.07), and clarity (4.87 vs. 2.80) compared to the control group. These findings suggest that EXACT framework significantly enhances user’s functions when using AI systems. However, further research is needed to explore its broader applicability in other contexts and utilize other cognitive functions. |
| format | Article |
| id | doaj-art-00426ae3977048acb0a6efbbccec27a6 |
| institution | OA Journals |
| issn | 2169-3536 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Access |
| spelling | doaj-art-00426ae3977048acb0a6efbbccec27a62025-08-20T02:35:05ZengIEEEIEEE Access2169-35362025-01-0113982089822810.1109/ACCESS.2025.357623411021617Enhancing AI Explainability Through the EXACT Framework: A User-Centric ApproachSara S. Alhasan0https://orcid.org/0009-0006-0643-8902Reem A. Alnanih1https://orcid.org/0000-0002-2428-0356Computer Sciences Department, Faculty of Computing and Information Technology, King Abdulaziz University, Jeddah, Saudi ArabiaComputer Sciences Department, Faculty of Computing and Information Technology, King Abdulaziz University, Jeddah, Saudi ArabiaThe increasing adoption of Artificial Intelligence (AI) in several industries has created a demand for user-centered explanations that align with how users think and understand concepts. This paper presents EXACT (EXplainable AI with Cognitive Theories), a novel framework that combines cognitive theories that explain how people think and understand with cognitive functions, focusing on perception, memory and language abilities, to improve users’ comprehension of and engagement with artificial intelligence technologies. By aligning cognitive functions with the design principles of Human-Computer Interaction (HCI), which promote user-centered intuitive systems. the framework addresses challenges related to making AI understandable to users with various levels of cognitive abilities. As a proof-of-concept, a self-diagnosis tool was created to demonstrate the framework’s effectiveness. Then, 60 participants were divided into a control group and an experimental group. Participants completed six tasks designed to evaluate their perception, memory, and language-related cognitive functions. The experimental group outperformed the control group across all tasks, demonstrating significantly improved performance. Subjective metrics also supported these findings: the experimental group reported higher levels of understanding (4.60 vs. 2.87), confidence (4.67 vs. 3.07), and clarity (4.87 vs. 2.80) compared to the control group. These findings suggest that EXACT framework significantly enhances user’s functions when using AI systems. However, further research is needed to explore its broader applicability in other contexts and utilize other cognitive functions.https://ieeexplore.ieee.org/document/11021617/Cognitive functionscognitive theoriesexplainable artificial intelligence (XAI)human-centered XAIhuman-computer interaction (HCI)medical diagnosis tool |
| spellingShingle | Sara S. Alhasan Reem A. Alnanih Enhancing AI Explainability Through the EXACT Framework: A User-Centric Approach IEEE Access Cognitive functions cognitive theories explainable artificial intelligence (XAI) human-centered XAI human-computer interaction (HCI) medical diagnosis tool |
| title | Enhancing AI Explainability Through the EXACT Framework: A User-Centric Approach |
| title_full | Enhancing AI Explainability Through the EXACT Framework: A User-Centric Approach |
| title_fullStr | Enhancing AI Explainability Through the EXACT Framework: A User-Centric Approach |
| title_full_unstemmed | Enhancing AI Explainability Through the EXACT Framework: A User-Centric Approach |
| title_short | Enhancing AI Explainability Through the EXACT Framework: A User-Centric Approach |
| title_sort | enhancing ai explainability through the exact framework a user centric approach |
| topic | Cognitive functions cognitive theories explainable artificial intelligence (XAI) human-centered XAI human-computer interaction (HCI) medical diagnosis tool |
| url | https://ieeexplore.ieee.org/document/11021617/ |
| work_keys_str_mv | AT sarasalhasan enhancingaiexplainabilitythroughtheexactframeworkausercentricapproach AT reemaalnanih enhancingaiexplainabilitythroughtheexactframeworkausercentricapproach |