Automatic modeling of student characteristics with interaction and physiological data using machine learning: A...

Area of Science:

• Educational Technology
• Artificial Intelligence in Education
• Learning Analytics

Background:

• Student characteristics significantly influence learning in online environments.
• Effective online education systems require dynamic assessment of these characteristics.
• Machine learning (ML) offers powerful tools for student modeling and adaptive learning.

Approach:

• This study reviews literature from 2015-2022 on ML applications for automatic student characteristic modeling.
• It identifies six key student characteristics amenable to automatic modeling.
• Data types, collection methods, and ML techniques are analyzed for each characteristic.

Key Points:

• Six student characteristics can be automatically modeled using ML.
• Various data sources and ML algorithms are employed for this purpose.
• The review highlights progress and identifies gaps in current research.

Conclusions:

• ML-driven student modeling is crucial for adaptive educational systems.
• This research provides a guide for educators and system designers.
• Future work should explore novel ML techniques to enhance model accuracy and expand modeling capabilities.