Related Experiment Video
Updated: Oct 5, 2025

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
Published on: December 15, 2023
Keep Calm and Do Not Carry-Forward: Toward Sensor-Data Driven AI Agent to Enhance Human Learning.
Kshitij Sharma1, Serena Lee-Cultura1, Michail Giannakos1
1Department of Computer Science, Norwegian University of Science and Technology, Trondheim, Norway.
Multimodal data from embodied learning games reveals a Carry Forward Effect, where student actions influence subsequent learning stages. Wristband and eye-tracking data are key for real-time adaptive feedback in educational settings.
Area of Science:
- Educational Technology
- Human-Computer Interaction
- Cognitive Science
Background:
- Multimodal Data (MMD) integration with embodied learning systems (e.g., Motion Based Educational Games, MBEG) offers insights into student interaction and learning.
- Real-time analysis of student-generated MMD from MBEG is complex and under-explored.
- Understanding the synergy between student movement and learning is crucial for designing supportive intelligent agents.
Purpose of the Study:
- To investigate the real-time use of MMD from embodied learning systems.
- To explore the cognitive and physiological dimensions of student progress within the "see-solve-move-respond" (S2MR) cycle.
- To introduce and analyze the Carry Forward Effect (CFE) and its impact on learning.
Main Methods:
- Conducted an in-situ study with 40 children (ages 9-12) playing MBEG for maths and language development.
- Utilized eye-tracking glasses, physiological wristbands, and Kinect for unobtrusive, continuous monitoring of student experiences.
- Analyzed MMD to understand cognitive and physiological states during the S2MR cycle.
Main Results:
- Introduced the Carry Forward Effect (CFE), a phenomenon where MMD-derived effects propagate through S2MR cycles.
- Identified congruence between CFE and learning performance to optimize feedback delivery.
- Demonstrated that wristband and eye-tracking data are crucial indicators for adaptive feedback in MBEG.
Conclusions:
- MMD provides valuable insights into student learning within embodied educational games.
- The CFE highlights the interconnectedness of cognitive and physiological states across learning stages.
- Real-time MMD analysis and adaptive feedback are significant for enhancing student performance in educational settings.
More Related Videos
Related Concept Videos
Observational Learning
Cognitive Learning
E. C. Tolman's theory of purposive behavior emphasizes that much behavior is goal-directed. He argued that to understand behavior, we must look at the entire sequence of actions leading to a goal. For instance, high school students study hard, not just due to past reinforcement but also to achieve the goal of getting into a good college.
Tolman introduced the idea that behavior is influenced by...
Non-equilibrium in the Cell
Purposive Learning
Introduction to Learning
In contrast to learned behaviors, unlearned behaviors such as crying, sexual...
Automatic Processing and Automatic Social Behavior

