Do educational chatbots raise project-course grades?
In a Malaysian team design course, students using an educational chatbot outperformed a traditional class on learning achievement, without clear gains on motivation or creative self-efficacy.
Source
Educational chatbots for project-based learning: investigating learning outcomes for a team-based design course
What they did
Sixty second-year TESOL/multimedia education students in Malaysia were assigned by class to a chatbot-supported project-based learning condition or a traditional control class. Both groups shared content, duration, and instructor; researchers compared learning achievement and several affective/perception measures.
What they found
The chatbot group scored significantly higher on course learning performance than the control group, with a large Cohen’s d. Need for cognition, motivational beliefs, creative self-efficacy, and perception of learning did not differ significantly between groups.
The limits
What it doesn't show
Class-level assignment (not individual randomization) limits causal certainty, and null effects on motivation measures mean chatbots were not a general engagement booster here. Findings are from one design course in one institution.
Key terms
- Educational chatbot
- A conversational software agent used to support teaching and learning tasks.
- Project-based learning
- Instruction organized around extended team projects that produce authentic products.
- Learning achievement
- Measured course performance showing what students learned or produced.
- Creative self-efficacy
- Belief in one’s ability to generate creative ideas or products.
- Need for cognition
- Tendency to enjoy and engage in effortful thinking.
Flashcards
Want these cards to stick?
Save the deck to NoteFren and study it with spaced repetition.
Quiz yourself
What outcome favored the chatbot group?
Common questions
Did the chatbot help every measured outcome?
No. Achievement improved, but motivation-related and creative self-efficacy measures did not differ significantly.
How were groups formed?
Two intact classes of 30 students each were assigned to chatbot or traditional conditions.
What was the control condition?
A traditional learning class covering the same content with the same instructor and duration.
Was the achievement difference large?
Yes; the reported Cohen’s d for learning performance was about 0.978.
More on Collaborative learning