| Creators: |
Lorch, Selina and Gebele, Jens and Brune, Philipp |
| Title: |
Towards Trustworthy AI: Evaluating SHAP and LIME for Facial Emotion Recognition |
| Item Type: |
Conference or Workshop Item |
| Event Title: |
(Proceedings of the) 58th Hawaii International Conference on System Sciences (HICSS) |
| Event Location: |
Waikoloa, HI, USA |
| Event Dates: |
January, 7-10, 2025 |
| Projects: |
TTZ-GZ |
| Page Range: |
pp. 7534-7543 |
| Date: |
7 January 2025 |
| Divisions: |
Informationsmanagement |
| Abstract (ENG): |
Explainable Artificial Intelligence (XAI) plays a crucial role in enhancing the transparency and interpretability of Machine Learning (ML) models, especially in sensitive domains like Facial Emotion Recognition (FER). This paper evaluates the effectiveness of the model-agnostic methods SHAP (Shapley Additive Explanations) and LIME (Local Interpretable Model-agnostic Explanations) in explaining ML decision-making for FER. Leveraging two established facial emotion databases, FER 2013 and RAF-DB, our research identifies key facial features of ML model predictions. Our results indicate that SHAP offers more consistent and reliable visualizations than LIME, effectively emphasizing critical regions such as the mouth, eyes, and cheeks, which align with the facial Action Units outlined by the Facial Action Coding System (FACS). This alignment enhances model interpretability, demonstrating how XAI can reconcile accuracy with transparency to foster the development of trustworthy AI systems in FER. Our study also shows that in complex domains like FER, XAI methods alone are insufficient; expert interpretation is crucial for applying insights from XAI visualizations, underscoring the need for interdisciplinary research to advance future studies in complex domains. |
| Forthcoming: |
No |
| Language: |
English |
| Uncontrolled Keywords: |
Explainable AI, SHAP, LIME, Model
Interpretability, Facial Emotion Recognition |
| Citation: |
Lorch, Selina and Gebele, Jens and Brune, Philipp
(2025)
Towards Trustworthy AI: Evaluating SHAP and LIME for Facial Emotion Recognition.
In: (Proceedings of the) 58th Hawaii International Conference on System Sciences (HICSS), January, 7-10, 2025, Waikoloa, HI, USA, pp. 7534-7543.
|
