Chatbot instruction appeared effective for participants lacking prior knowledge of posing questions for improvement (path J, n = 16)¶

Claim · All claims
Evidence · 1 study · design r2 · q2
Currency · newest study 2025 · not yet checked against its sources · not reviewed by a person

Subclaims¶

q2 i? More than half of participants (n = 16) on path J — who judged they did not know how to pose questions but answered CCQs correctly — improved after chatbot instruction. → Michael Pin-Chuan Lin 2025

Evidence¶

Michael Pin-Chuan Lin 2025¶

Michael Pin-Chuan Lin, Daniel H. Chang, Philip H. Winne. (2025). A proposed methodology for investigating student-chatbot interaction patterns in giving peer feedback. Education Tech Research Dev. https://doi.org/10.1007/s11423-024-10408-3

q2 · i? · design · r2

First-session path counts (Table 5) in the 23-participant study; the article interprets path J as chatbot instruction being effective for participants who judged they lacked the skill. The n = 16 count is descriptive; no effect size is printed.

"When learning how to pose questions for improvement (Table 5), more than half of the participants (n = 16) who followed path J exhibited improved performance after receiving chatbot instruction."

Discussion¶

Related Claims¶

• Students were often overconfident about their understanding of how to give peer feedback after chatbot instruction — related
• Adult learners perceive conversational AI as thinking partners that support problem exploration without direct instruction — related