L@S

Modeling @ Scale (1)

Mon Jun 29, 10:45 AM–12:00 PM · North 205

Learner & Student Modeling Learning at Scale & MOOCs

★ Notable speakers

Justin Reich ★★ — Executive Director of MIT Teaching Systems Lab; author of 'Failure to Disrupt'; large-scale MOOC research (HarvardX/MITx); learning analytics; teacher preparation and tech policy

René Kizilcec ★★ — Learning at scale; algorithmic fairness and equity in digital education

Kevyn Collins-Thompson ★ — Statistical text readability prediction; vocabulary learning; adaptive intelligent reading tutors

Kirk Vanacore ★ — Learning analytics; educational data mining; causal inference in tutoring; AI annotation of learning discourse at scale

Jionghao Lin ★ — Dialogue-based intelligent tutoring, NLP for educational feedback, AI-driven tutor training

A session grouping L@S papers on modeling approaches and statistical methods applied to learning data at scale.

3 talks in this session

Augmenting Knowledge Tracing With Self-Regulated Learning Indicators for Reliable Skill-Mastery Estimation

Yujing Zhang, Xianghui Meng, Jionghao Lin

Adaptive & Personalized Learning Knowledge Tracing Self-Regulated Learning

From Tutor Moves to Tutoring States: Modeling the Timing and Sequencing of Pedagogical Strategies for Student Engagement

Kirk Vanacore, Jinsook Lee, Bakhtawar Ahtisham, Sarah Shaw, Justin Reich

Learner & Student Modeling Affect & Engagement Detection NLP & Discourse Analysis

Measuring Simulation Fidelity via Statistical Detectability: A Diagnostic Framework for AI-Generated Tutoring Conversations

Michael Ion, Kevyn Collins-Thompson

Generative AI & Large Language Models Conversational AI & Chatbot Tutors Synthetic Data & Simulated Learners