2023

Haque AKM Bahalul; Islam A.K.M. Najmul; Mikalef Patrick

The growing attention on artificial intelligence-based decision-making has led to research interest in the explainability and interpretability of machine learning models, algorithmic transparency, and comprehensibility. This renewed attention on XAI advocates the need to investigate end user-centric explainable AI, due to the universal adoption of AI-based systems at the root level. Therefore, this paper investigates user-centric explainable AI from a recommendation systems context. We conducted focus group interviews to collect qualitative data on the recommendation system. We asked participants about the end users' comprehension of a recommended item, its probable explanation and their opinion of making a recommendation explainable. Our finding reveals end users want a non-technical and tailor-made explanation with on-demand supplementary information. Moreover, we also observed users would like to have an explanation about personal data usage, detailed user feedback, authentic and reliable explanations. Finally, we proposed a synthesized framework that will include end users in the XAI development process.