Revoicing support from an APT conversational agent significantly increases learning gains in 9th grade biology collaborative discussions¶

Claim · All claims
Evidence · 1 study · causal r2 · q3 · i1 small
Currency · newest study 2014 · not yet checked against its sources · not reviewed by a person

Subclaims¶

q3 i1 Students in the Revoicing condition learned significantly more between Pretest and Posttest with an effect size of 0.34 standard deviations. → Adamson 2014

Evidence¶

Adamson 2014¶

Adamson, D., Dyke, G., Jang, H., & Rosé, C. P. (2014). Towards an Agile Approach to Adapting Dynamic Collaboration Support to Student Needs. International Journal of Artificial Intelligence in Education. https://doi.org/10.1007/s40593-013-0012-6

q3 · i1 · causal · r2

The Dyke et al. (2013) study used a 2×2 between-subjects factorial design manipulating Revoicing and APT Feedback with 9th grade biology students in a Diffusion Lab task. The study found "a significant main effect of Revoicing" with "an effect size of 0.34 standard deviations."

"Students showed significant learning gains in all conditions, and there was a significant main effect of Revoicing such that students in the Revoicing condition learned significantly more between Pretest and Posttest, with an effect size of 0.34 standard deviations."

Discussion¶

Related Claims¶

• Positive Feedback for APT engagement does not positively impact learning in collaborative discussions — reports the opposite
• Conversational-agent prompts improve student dialogue outcomes at both individual and dyad levels — related
• In the Academically Productive Talk system, review material and higher student skill level normally yielded better learning results — related