Student teachers generated 2,181 Cipherbot conversations, dominated by topic inquiries targeting deepening understanding and clarifications¶
Claim · All claims
Evidence · 1 study · qualitativer2·q2
Currency · newest study 2025 · not yet checked against its sources · not reviewed by a person
Subclaims¶
Reading the evidence codes
q is the design tier, i the impact, n the sample, and the kind with its r
the rigour judged within that kind: what each code means.
This claim: no standardized effect is recorded in observations/ for it yet, so no benchmark reading is possible.
q2 i? Across course assessments, students generated 2,181 conversations, 91% topic inquiries versus 8% follow-ups, with 1,852 question chats. → Chaaban 2025
Evidence¶
Chaaban 2025¶
Chaaban, Y., Jung, S.-G., Medina, J., Azem, J. Y., Salminen, J., & Jansen, B. J. (2025). Examining Student Teachers' Agency in an AI-Supported Learning Environment: Q Methodology Research. International Journal of Artificial Intelligence in Education. https://doi.org/10.1007/s40593-025-00529-y
q2 · i? · qualitative · r2
Observational engagement analytics automatically generated by Cipherbot during one semester of the classroom management course, reporting "2,181 conversations" and "1,852 chats were questions" across assessment tasks.
"Students consulted with Cipherbot on these assessments and generated 2,181 conversations throughout the semester, including 91% topic inquiries compared to 8% follow-ups. A total of 1,852 chats were questions"
Discussion¶
Related Claims¶
- A few-shot FastFit classifier maps conversational AI teaching assistant questions to 43 curriculum topic labels with 80.0% accuracy on a 70-question gold set — related
- The FastFit classifier slightly outperforms GPT-4 used directly under the same closed-label prompt on the same gold set (0.800 vs. 0.786 accuracy) — related
- Classifier errors cluster into three interpretable patterns, and the unknown abstention class is well classified (F1 = 0.93), reliably filtering off-topic chat — related
- An agentic AI instructor sustained and deepened student engagement across successive course modules in a field deployment — related
- Interactive dialogue with the AI tool, available only in some sites, promoted deeper engagement and student agency during revision — related
Page metadata
| Field | Value |
|---|---|
type |
claim |
id |
cipherbot-conversation-analytics-2181 |
title |
Student teachers generated 2,181 Cipherbot conversations, dominated by topic inquiries targeting deepening understanding and clarifications |
description |
Student teachers generated 2,181 Cipherbot conversations, dominated by topic inquiries targeting deepening understanding and clarifications |
status |
review |
evidence_strength |
weak |
newest_evidence |
2025 |
generated |
by process:wiki-ingest on 2026-10-27 |
trust |
unverified — no one has confirmed this page's content |
sources |
1 — chaaban-2025 |
Frontmatter is the page's machine-readable record — see the Schema & Guide.