The fields of Learning Analytics and Educational Data Mining have produced a broad range of methods for real-time detection of actionable features of student learning and behavior within intelligent tutoring systems (ITSs). Such analytics can augment the perceptions of both human teachers and AI tutors, and may thereby inform more effective instruction. However, existing authoring and deployment environments for ITSs do not typically support the integration of custom analytics into running ITSs. We are extending the CTAT/TutorShop architecture for ITS authoring and deployment to enable advanced forms of tutor adaptivity, and to support a broad range of user-facing learning analytics tools.
Holstein, K., Yu, Z. Popescu, O., Sewall, J., McLaren, B. M., & Aleven, V. (2018). Opening up an intelligent tutoring system development environment for extensible student modeling. To appear in Proceedings of the 19th International Conference on Artificial Intelligence in Education (AIED’18). [pdf]
CTAT Detector Library