"Time-series analysis for modelling the behavior of learners in MOOCs"

The high-resolution learner activity data that modern online learning environments collect provide a unique opportunity to study the behavior of online learners and to develop tools and mechanisms for personalized teaching and learning. Applications include adaptive learning algorithms that provide timely feedback and recommend activities to individual students, teacher dashboards that provide actionable insights to teachers, early warning systems that identify students at risk, and more. My research centers on these directions in K12 blended learning environments and MOOCs. In the talk, I will focus on one line of research: time-series analysis of MOOC data in order to discover effective and ineffective learning behaviors, detect unethical behaviors, and study how they evolve over time.

Bio: Giora Alexandron is a Senior Scientist (Assistant Professor) in the Department of Science Teaching, Weizmann Institute of Science, and the head of the Computational Approaches to Science Education (CASEd) research group. His research combines science education and the learning sciences, artificial intelligence, and human-computer interaction, in order to study and develop learning environments that are more adapted to the needs of different learners. His main focus is on K-12 science education and within it, on Teacher:AI partnership – how AI can work alongside teachers in order to assist them in providing more personalized instruction. In addition, he is also working on MOOCs and on machine learning education for high school students. Giora’s research is frequently published in leading international academic journals and conferences, and he served as organiser, track chair, and program committee member of various conferences in his field.