A Large-Scale, Open-Domain, Mixed-Interface Dialogue-Based ITS for STEM

We present Korbit, a large-scale, open-domain, mixed-interface, dialogue-based intelligent tutoring system (ITS). Korbit uses machine learning, natural language processing and reinforcement learning to provide interactive, personalized learning online. Korbit has been designed to easily scale to thousands of subjects, by automating, standardizing and simplifying the content creation process. Unlike other ITS, a teacher can develop new learning modules for Korbit in a matter of hours. To facilitate learning across a wide range of STEM subjects, Korbit uses a mixed-interface, which includes videos, interactive dialogue-based exercises, question-answering, conceptual diagrams, mathematical exercises and gamification elements. Korbit has been built to scale to millions of students, by utilizing a state-of-the-art cloud-based micro-service architecture. Korbit launched its first course in 2019 and has over 7, 000 students have enrolled. Although Korbit was designed to be open-domain and highly scalable, A/B testing experiments with real-world students demonstrate that both student learning outcomes and student motivation are substantially improved compared to typical online courses.

[1]  Johanna D. Moore,et al.  A comparative evaluation of socratic versus didactic tutoring , 2001 .

[2]  Arthur C. Graesser,et al.  Intelligent Tutoring Systems with Conversational Dialogue , 2001, AI Mag..

[3]  Arthur C. Graesser,et al.  AutoTutor: an intelligent tutoring system with mixed-initiative dialogue , 2005, IEEE Transactions on Education.

[4]  Albert T. Corbett,et al.  Cognitive Tutor: Applied research in mathematics education , 2007, Psychonomic bulletin & review.

[5]  Lisa Kirtman Online Versus In-Class Courses: An Examination of Differences in Learning Outcomes , 2009 .

[6]  J. Folsom-Kovarik,et al.  Plan Ahead : Pricing ITS Learner Models , 2010 .

[7]  J. Daniel Making Sense of MOOCs: Musings in a Maze of Myth, Paradox and Possibility , 2012 .

[8]  John Champaign,et al.  Learning in an introductory physics MOOC: All cohorts learn equally, including an on-campus class , 2014 .

[9]  Arthur C. Graesser,et al.  AutoTutor and Family: A Review of 17 Years of Natural Language Tutoring , 2014, International Journal of Artificial Intelligence in Education.

[10]  Joseph K. Cavanaugh,et al.  A Large Sample Comparison of Grade Based Student Learning Outcomes in Online vs. Face-to-Face Courses. , 2015 .

[11]  Kenneth R. Koedinger,et al.  Learning is Not a Spectator Sport: Doing is Better than Watching for Learning from a MOOC , 2015, L@S.

[12]  Ghada R. El Said,et al.  Exploring the factors affecting MOOC retention: A survey study , 2016, Comput. Educ..

[13]  James A. Kulik,et al.  Effectiveness of Intelligent Tutoring Systems , 2016 .

[14]  D. Otto,et al.  It’s the learning, stupid! Discussing the role of learning outcomes in MOOCs , 2018, Open Learning: The Journal of Open, Distance and e-Learning.

[15]  Maria Chang,et al.  Adaptive Visual Dialog for Intelligent Tutoring Systems , 2018, AIED.

[16]  Shazia Afzal,et al.  Preliminary Evaluations of a Dialogue-Based Digital Tutor , 2018, AIED.

[17]  Randy Jensen,et al.  ITADS: A Real-World Intelligent Tutor to Train Troubleshooting Skills , 2018, AIED.