research
research directions and representative works
Modeling Self-regulated Learning using Learning Analytics
To design and develop XAI-driven interventions that help individuals learn, practice, and develop self-regulated learning skills, it is crucial to understand how these skills manifest in computer-based learning environments. To achieve this, I leverage machine learning, data mining (e.g, sequential pattern mining), and statistical methods (e.g., hierarchical linear modeling), grounded in learning theories, to measure the application of these skills.
Leveraging XAI to Design and Develop Interventions that Support Self-regulated Learning
I explore how XAI-driven interventions can foster self-regulated learning and metacognitive abilities through the lens of HCI and learning theories. These skills are crucial not only for students but also as lifelong competencies that empower individuals across diverse contexts. By developing such interventions, I aim to help learners understand the reasoning behind AI-generated feedback and recommendations, enabling them to make more informed learning decisions. Ultimately, this work contributes to our understanding of how XAI can be leveraged to support humans in becoming better self-regulated learners.
Evaluating AI systems for Fairness
Understanding how such AI-powered systems support self-regulated learning, and whether they work equitably for diverse groups of learners, including neurodiverse learners (e.g., individuals diagnosed with ADHD), is crucial for ensuring that these interventions do not reinforce existing disparities, but instead empower all learners to develop effective learning strategies and metacognitive skills.