Engagement metrics — time, actions, and interaction depth with AI tools — are measured in engagement-forecasting-its, genai-tutor-engagement-patterns, understanding-student-effort-response-time, and access-not-enough-ai-tutoring-2026: take-up and sustained use are often the binding constraints on AI effectiveness (learning-analytics, student-experience).
Related Pages
- lets-chat-chatbot-outreach-2026 — A/B and DFW outcomes from chatbot outreach
- access-not-enough-ai-tutoring-2026 — Usage minutes and stories as engagement outcomes
- scheu-mobile-chatbot-journaling-motivation-2026 — Response length (chars/prompt) as behavioral engagement metric
- cross-subject-validity-delayed-start — Delayed start frequency as a generalizable engagement metric with cross-subject predictive validity
- framing-5-percent-problem-teachers-persistence -- Teachers identify four dimensions of low persistence in adaptive math platforms (motivation, cognitive roadblocks, resilience, context) and prioritize diagnosis over aggregate metrics.
- ai-assisted-learning-modes-eeg — AI-Assisted Learning Modes (EEG Study)
- medgame-llm-medical-education-gamification — MedGame: Storytelling Gamification Empowered by Large Langua
📎 23 other pages tagged engagement-metrics
- Access is Not Enough: Human Support Improves Engagement with AI Tutoring
- An exploratory behavioral and electroencephalographic study of artificial intelligence-assisted learning modes in high school students
- Comparing Generative AI and teacher feedback: student perceptions of usefulness and trustworthiness
- Confident yet Concerned: Inconsistencies in Computing Students' Attitudes on Cybersecurity
- Cross-Subject Predictive Validity for Learning Outcomes of Delayed Start Behavior
- Data Annotations as Pedagogical Hints: From Subjective Labels to Critical Thinking
- Design and Implementation of a Real-time Multi-site Immersive Learning System Using Photon Fusion
- Designing a mobile chatbot-based learning journaling system for intrinsic motivation and engagement
- Engagement Intensity as a Learner-Modeling Signal for Adaptive AI Ethics Instruction
- Framing the 5% Problem: Teachers' Perspectives on Persistence in Educational Technology
- From Heuristics to Analytics: Forecasting Effort and Progress in Online Learning
- Hypergamigication Through Integrating Game Engines and Learning Management Systems: Ender's Game
- Less Deliberate in Teams: Student LLM Use Across Individual and Collaborative Work
- Let's Chat: Leveraging Chatbot Outreach for Improved Course Performance
- Leveraging Physiological Signals to Predict Exam Outcomes with Machine Learning
- MedGame: Storytelling Gamification Empowered by Large Language Models for Medical Education
- Not All Students Engage Alike: Multi-Institution Patterns in GenAI Tutor Use
- SAVVY: Student Attention Visualization for Video-based Learning Analysis
- Simulating Learners' Task-Selection Strategies and System Constraints in Mastery Learning
- The Missing Evaluation Axis: What 10,000 Student Submissions Reveal About AI Tutor Effectiveness
- To Facilitate or not to Facilitate: Human and LLM Facilitator Tendencies in Online Discussions
- Understanding Student Effort Using Response-Time Propensities During Problem Solving
- When AI Agents Teach Each Other: Discourse Patterns Resembling Peer Learning in the Moltbook Community