In the Academically Productive Talk system, review material and higher student skill level normally yielded better learning results¶

Claim · All claims
Evidence · 1 study · review r2 · q2
Currency · newest study 2015 · not yet checked against its sources · not reviewed by a person

Subclaims¶

q2 i? The effectiveness of an agile multi-strategy conversational-agent system depended on material type and student skill level, with review material and higher skill level normally yielding better results. → McManus 2015

Evidence¶

McManus 2015¶

McManus, M. M., & Aiken, R. M. (2015). Supporting Effective Collaboration: Using a Rearview Mirror to Look Forward. International Journal of Artificial Intelligence in Education, 26, 365–377. https://doi.org/10.1007/s40593-015-0068-6

q2 · i? · review · r2

Narrative review of Adamson et al.'s experiments on the Bazaar platform, where an automated Academically Productive Talk system gave positive feedback in collaborative chat. The article reports the system's effectiveness 'depends on several factors, such as the type of the material and the skill level of each student', and that 'Review material and a higher student skill level normally yielded better results in learning.'

"Review material and a higher student skill level normally yielded better results in learning."

Discussion¶

Related Claims¶

• Conversational-agent prompts improve student dialogue outcomes at both individual and dyad levels — related
• System-controlled adaptive instruction does not necessarily yield higher transfer than nonadaptive static approaches — related
• Positive Feedback for APT engagement does not positively impact learning in collaborative discussions — a narrower finding that bears on this claim
• The effectiveness of specific APT facilitation strategies is context-specific, depending on material difficulty and learner skill level — related
• Revoicing support from an APT conversational agent significantly increases learning gains in 9th grade biology collaborative discussions — related