Explainable AI In Education : Current Trends, Challenges, And Opportunities

Abstract

Explainable Artificial Intelligence (XAI) has garnered significant attention in recent years to increase the transparency of AI models and systems and aid in decision-making. This is particularly important in the education sector, where AI systems are being increasingly used in LMS (Learning Management Systems) and EDM (Educational Data Mining) tools to support the learning and assessment of students. In this paper, based on the existing research and literature on XAI we assert that while XAI in education shares some characteristics with the wider application of explainability approaches in other domains, it also has its own distinctive stipulations that differ from other domains. We aim to address these disparate characteristics by overviewing the XAI approaches in literature from their inception to the current state-of-the-art. We then address various back-drops to appropriately adjust these methods to facilitate favorable explanations for students and finally we identify research gaps in various parameters and suggest potential future research avenues by tethering the identified gaps with advancements in the field.