Chatbot engagement was highly uneven: 8 of 15 voluntary users interacted continuously while 7 interacted superficially¶

Claim · All claims
Evidence · 1 study · design r3 · q2
Currency · newest study 2026 · checked against its sources 2026-10-20 (automated, 1 of 1 entry) · not reviewed by a person

Subclaims¶

q2 i? Interaction-log analysis in the third cycle showed a small subset of students (8 out of 15) interacted continuously, averaging 23.6 messages and 10.9 conversational runs, while the rest averaged 1.3 messages and almost no conversational runs. → Hilliger 2026

Evidence¶

Hilliger 2026¶

Hilliger, I., Pérez-Sanagustín, M., González, C., Villalobos, E. and Celis, S. (2026). A GAI-Based Chatbot for Scaffolding Self-Regulated Learning: Insights from a Design-Based Research Approach. Journal of Learning Analytics, 13(1), 74–88. https://doi.org/10.18608/jla.2026.9143

q2 · i? · design · r3

Analysis of interaction logs from 15 of 34 enrolled students who voluntarily used the web-based chatbot in Education and Society during first semester 2024. Superficial users (7 of 15) averaged 1.3 messages (95% CI = [0.59, 1.98]) and 0.14 conversational runs.

"a small subset of students (8 out of the 15) interacted continuously throughout the academic period , producing on average 23.6 messages (95% Confidence Interval = [1.89, 45.36]), participating in 10.9 conversational runs"

Discussion¶

Related Claims¶

• Dialogic competence is a prerequisite for meaningful engagement with LLM-based chatbots — related
• Students primarily used the Socratic-tutor chatbot as a study aid aligned with existing study habits rather than for the intended Socratic reflection — related
• Telegram-based chatbot use declined after initial novelty, with platform friction cited as a barrier — related
• K-2 students showed sustained high engagement with Puzzlets, choosing it as their first station choice 27 out of 36 times — related
• Pilot engagement was strong with month-over-month user retention, and teachers used the AI primarily for consumption rather than creation — related
• Primary metrics improved during US holidays, attributed to more motivated voluntary users — related
• Chatbot usage analytics show substantial after-hours demand, with 36.8% of interactions occurring outside standard working hours — related
• In a voluntary pilot of a GenAI practice platform, 34 of 95 registrants attempted at least one question, generating 230 submissions with highly uneven engagement — related
• Students dynamically switched between Socratic Inquiry and Transactional Delegation as deadlines approached and task novelty changed (the Strategic Dance) — related
• Voluntary StatBot use was highly uneven and deadline-driven, with about 27% of students never using the chatbot — related
• Learners engaged extensively with the chatbot, overwhelmingly communicating in Japanese rather than English — related
• Voluntary classroom uptake of teacher-assigned AI discussions was high on average (85.0% classroom participation) but heterogeneous across teachers and discussions — related
• Students who continued feedback conversations with ChatGPT perceived more utility in AI feedback than one-shot users — related
• Students in real-world chatbot deployments exhibit lower scaffolding uptake than benchmarks assume, frequently bypassing the chatbot's pedagogical framing — related