Teaching a ChatGPT agent improves students' self-regulated learning, specifically self-efficacy and use of cognitive strategies¶

Claim · All claims
Evidence · 1 study · causal r1 · q2 · i3 large
Currency · newest study 2024 · checked against its sources 2026-10-19 (automated, 1 of 1 entry) · not reviewed by a person

Subclaims¶

q2 i3 The experimental group achieved significantly higher post-test self-efficacy than the control group (F = 37.26, η2 = 0.75). → Angxuan Chen 2024 q2 i3 The experimental group achieved significantly higher post-test cognitive strategies scores than the control group (F = 18.97, η2 = 0.61). → Angxuan Chen 2024

Evidence¶

Angxuan Chen 2024¶

Angxuan Chen, Yuang Wei, Huixiao Le, Yan Zhang. (2024). Learning-by-Teaching with ChatGPT: The Effect of Teachable ChatGPT Agent on Programming Education. arXiv. https://arxiv.org/abs/2412.15226 doi:10.48550/arxiv.2412.15226

q2 · i3 · causal · r1

ANCOVA on an adapted MSLQ-based SRL questionnaire administered pre and post; the experimental group "achieved significantly higher scores in self-efficacy (F = 37.26, p < 0.001, η2 = 0.75), and cognitive strategies (F = 18.97, p < 0.001, η2 = 0.61)".

"The ANCOV A results (See Table 4) demonstrated that the experimental group, which utilized the ChatGPT teachable agent, achieved significantly higher scores in self-efficacy (F = 37.26, p < 0.001, η2 = 0.75), and cognitive strategies (F = 18.97, p < 0.001, η2 = 0.61) compared to the control group."

Discussion¶

Learner Variables¶

• Motivation — outcome: instruction changes it
• Self-Regulation — outcome: instruction changes it

Related Claims¶

• Students who teach a ChatGPT teachable agent in natural language achieve greater knowledge gains than students who learn the same material from online videos — related
• Teaching a ChatGPT agent does not significantly improve code correctness compared with writing code independently from videos — related
• Teaching a ChatGPT agent does not significantly change students' test anxiety — related
• A within-subjects pilot with 27 professional software engineers found statistically significant self-reported self-efficacy gains across all 10 assessed skill areas after completing the cc-self-train curriculum — related
• Students with moderate initial CT levels show substantially greater self-efficacy gains than high-CT and low-CT peers, an 'Optimal Development Zone' effect — related
• The article is situated within research on self-regulated learning strategies in educational contexts — related
• Learning with a ChatGPT-based flipped learning guiding approach significantly improves students’ performance, self-efficacy, learning attitudes, intrinsic motivation and creative thinking in a courseware project — related
• ChatGPT-integrated instruction produced significantly higher post-test writing motivation scores than conventional instruction among EFL learners, with a medium effect size — related
• GCLA use improves cognitive and behavioral engagement and self-efficacy compared with traditional ChatGPT use in blended learning — related
• AI-mediated language instruction fosters self-regulated learning among EFL learners more than traditional instruction — related
• Adding a teachable agent to the standard science curriculum improved fourth-graders' learning gains on both curriculum tests and researcher-designed hierarchical reasoning tests — related
• All participants reported higher teaching self-efficacy after the teaching-simulation training — related
• Iterative testing engagement during AI agent creation predicts CT self-efficacy gains after controlling for initial self-efficacy — related
• Pilot studies in computing-related majors report measurable improvements in student engagement, self-efficacy, and learning outcomes — related
• Students using an AR system for plant study showed higher learning motivation than a control group — related
• Conversational-agent prompts improve student dialogue outcomes at both individual and dyad levels — related