Related Experiment Video
Updated: Jun 24, 2025

Author Spotlight: Addressing Technical and Subjective Challenges in Measuring Classroom Attention
Published on: December 15, 2023
Automatic Classification of Online Discussions and Other Learning Traces to Detect Cognitive Presence
Verena Dornauer1, Michael Netzer1, Éva Kaczkó1,2
1Institute of Medical Informatics, UMIT TIROL - Private University for Health Sciences and Health Technology, Eduard Wallnöfer Zentrum 1, Hall in Tirol, 6060 Austria.
Researchers developed a German-language classifier to automatically detect students' cognitive presence in online courses using linguistic analysis. This tool, based on the Community of Inquiry framework, achieved 82% accuracy without needing additional learning traces.
Area of Science:
- Educational Technology
- Online Learning
- Artificial Intelligence in Education
Background:
- Cognitive presence is vital for meaningful online learning within the Community of Inquiry (CoI) framework.
- Real-time dashboards visualizing cognitive presence can aid instructors in monitoring and supporting student progress.
- Current classifiers often rely solely on linguistic analysis of student posts, with limited exploration of other learning traces.
Purpose of the Study:
- To develop and evaluate a German-language classifier for cognitive presence in online courses.
- To investigate whether incorporating additional learning traces (e.g., file attachments, tagging) improves classifier accuracy compared to linguistic analysis alone.
- To create a foundational dataset for future research on cognitive presence in German online learning environments.
Main Methods:
- Utilized a dataset of 1,521 manually coded meaningful units from a German online university course.
- Employed the Linguistic Inquiry and Word Count (LIWC) tool for linguistic feature extraction.
- Included additional learning traces such as file attachments, tagging, and glossary term usage.
- Applied k-nearest neighbor, random forest, and multilayer perceptron classification models.
Main Results:
- Achieved a maximum accuracy of 82% and a Cohen's κ of 0.76 for the cognitive presence classifier.
- The inclusion of additional learning traces did not significantly enhance the predictive performance of the classifier.
- Successfully developed an automatic classifier for cognitive presence in German online courses based on linguistic analysis.
Conclusions:
- An automatic classifier for detecting cognitive presence in German online courses has been developed, primarily using linguistic analysis.
- The developed classifier represents a step towards creating real-time teacher dashboards for monitoring student engagement.
- This study provides the first fully CoI-coded German dataset, valuable for future research in cognitive presence and online learning.
More Related Videos
10:43Eye-tracking Technology and Data-mining Techniques used for a Behavioral Analysis of Adults engaged in Learning Processes
Published on: June 10, 2021
12:55Multimodal Protocol for Assessing Metacognition and Self-Regulation in Adults with Learning Difficulties
Published on: September 27, 2020
Related Concept Videos
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...
Metacognition
Cognitivism
Previously dominated by behaviorism, which prioritized observable behaviors and largely ignored mental processes, psychology transformed in the 1950s. Cognitive psychologists argue that understanding how we think and process...
Introduction to Cognitive Psychology
This field emerged in the mid-20th century, following a period dominated by behaviorism, which...
High-Level and Low-Level Awareness
Higher Mental Functions of Brain: Learning and Memory