Students preferring combination-style chatbots had higher total EBAPS scores than students preferring direct-answer chatbots (nominal significance only)¶

Claim · All claims
Evidence · 1 study · associational r2 · q2
Currency · newest study 2026 · not yet checked against its sources · not reviewed by a person

Subclaims¶

q2 i? Dunn's post-hoc test with Bonferroni correction revealed statistically different total-score distributions between the Answer and Combination groups (p = 0.029), with the Combination group higher. → Amogh Sirnoorkar and Omkar Mamidpalliwar 2026

Evidence¶

Amogh Sirnoorkar and Omkar Mamidpalliwar 2026¶

Amogh Sirnoorkar and Omkar Mamidpalliwar. (2026). Students' Epistemological Beliefs and their Chatbot Preferences in AI-mediated Physics Learning. https://arxiv.org/abs/2607.29385 doi:10.48550/arxiv.2607.29385

q2 · i? · associational · r2

Dunn's post-hoc test with Bonferroni correction following the significant omnibus Kruskal-Wallis test on total EBAPS scores; Table II prints means of 69.7% (Combination) versus 67.9% (Answer). No effect size is printed for the pairwise contrast.

"For the total score, the test revealed that Answer and Combination groups had statistically different distributions ( p = 0.029). Furthermore, students preferring combination-style chatbot had higher EBAPS scores than those who prefer direct answers."

Discussion¶

Learner Variables¶

• Learning-Style Preferences — predictor: learners reporting different styles differed here; not a test of matching instruction to style

Related Claims¶

• Reflective thinking dimensions correlate positively with learning process/expert knowledge, and most correlate positively with learning effort and negatively with innate/fixed ability and certainty of knowledge — the general claim this finding bears on, with the studies behind it
• Chatbot preference groups differed in total EBAPS and Axis 4/5 scores at the nominal level, with small effect sizes, but not after Bonferroni adjustment — a broader claim this one bears on
• Combination-preferring students scored higher than answer-preferring students on evolving-knowledge (Axis 4) and source-of-ability (Axis 5) EBAPS dimensions — possibly the same claim (merge candidate)
• No statistically significant EBAPS differences were observed for Axes 1–3 or between guided-inquiry and answer-oriented chatbot preferrers — related
• Most introductory physics students preferred a combination chatbot (guidance first, answers when stuck), while few preferred pure guided Q&A — related