ExplainabilityTrustworthinessTransparencycs.AI
Toward Personalized XAI: A Case Study in Intelligent Tutoring Systems
Cristina Conati, Oswald Barral, Vanessa Putnam, Lea Rieger
December 10, 2019
arXiv.org
1 citations
Key Takeaways
-
Explanations build trust in AI systems: When students received explanations for AI-generated hints in the tutoring system, they reported higher trust in those hints and found them more useful, suggesting that transparency about how AI makes decisions can improve user confidence.
-
One-size-fits-all explanations may not work: The study found that different students benefited differently from explanations based on their personality traits and cognitive abilities, indicating that effective AI explanations should be tailored to individual user characteristics rather than presented identically to everyone.
-
Personalized XAI affects both learning and engagement: Student learning gains and their willingness to use explanations varied based on individual differences, demonstrating that personalization in explainable AI isn't just about user preference—it has measurable impacts on educational outcomes.
-
Explainability increases intention to reuse AI systems: Beyond immediate learning benefits, students who received explanations for AI hints showed greater intention to use the system again, suggesting that understanding AI decisions encourages continued engagement with AI-assisted tools.
Abstract
Our research is a step toward ascertaining the need for personalization, in XAI, and we do so in the context of investigating the value of explanations of AI-driven hints and feedback are useful in Intelligent Tutoring Systems (ITS). We added an explanation functionality for the adaptive hints provided by the Adaptive CSP (ACSP) applet, an interactive simulation that helps students learn an algorithm for constraint satisfaction problems by providing AI-driven hints adapted to their predicted level of learning. We present the design of the explanation functionality and the results of a controlled study to evaluate its impact on students' learning and perception of the ACPS hints. The study includes an analysis of how these outcomes are modulated by several user characteristics such as personality traits and cognitive abilities, to asses if explanations should be personalized to these characteristics. Our results indicate that providing explanations increase students' trust in the ACPS hints, perceived usefulness of the hints, and intention to use them again. In addition, we show that students' access of the explanation and learning gains are modulated by user characteristics, providing insights toward designing personalized Explainable AI (XAI) for ITS.