Mirror, Mirror, on theWall" - Promoting Self-Regulated Learning using Afective States Recognition via Facial Movements

Prior research suggests that afective states of self-regulated learning can be used to improve learners' cognitive processes and their learning outcomes. However, little research explored the efect of using facial movements to detect learners' afective states on selfregulated learning. In this work, we designed, implemented, and evaluated Mirror: a self-regulated learning tool that applies facial expression recognition to support learners' refections in videobased learning. We conducted two studies to identify user needs (with 12 participants) and to evaluate the tool (with 16 participants). The results show that, after watching a video, participants benefted from using Mirror through diferent refection processes, e.g., gaining a deeper understanding of their learning experiences through self-observation and attributing causes for their learning afects through self-judgment. Meanwhile, we also identifed several ethical concerns, e.g., users' agency of handling the uncertainty of AI, reactivity towards outcome-based AI, over-reliance on "positive" AI results, and fairness of AI informed decision-making.