Stephanie Lin
Papers
1
Total Citations
24
H-Index
1
About
Stephanie Lin is a researcher at the intersection of human-computer interaction and AI-augmented education, best known for her pioneering work on teachable agents and curiosity-driven learning environments. Her most cited paper, "Curiosity Notebook: A Platform for Learning by Teaching Conversational Agents" (2020, 24 citations), introduces a novel system where students learn by instructing AI agents—a paradigm that transforms passive knowledge consumption into active teaching. This work addresses a critical gap in educational technology: the difficulty of assessing learning processes when humans teach AI. Lin's platform enables fine-grained analysis of how teaching behaviors (e.g., explanation strategies, question-asking) correlate with learning outcomes, offering researchers a powerful tool to study metacognition and knowledge construction. Her contributions have been recognized for bridging cognitive science and AI design, with implications for personalized tutoring systems. By making the invisible process of learning-by-teaching visible, Lin's research provides both a practical platform for classrooms and a theoretical framework for understanding how we learn when we teach. Her work continues to influence the design of interactive AI that fosters deeper, more reflective learning.
Research Focus
Key Achievements
Top Papers
- 1