VanLehn (2011) found step-based intelligent tutoring systems nearly as effective as average human tutors, and both more effective than no tutoring but less effective than expert human tutors¶

Claim · All claims
Evidence · 1 study · review r2 · q2
Currency · newest study 2015 · checked against its sources 2026-10-31 (automated, 1 of 1 entry) · not reviewed by a person

Subclaims¶

q2 i? Step-based ITSs were nearly as effective as average human tutors; neither matched expert human tutors; both beat providing domain content without tutoring. → Benedict du Boulay 2015

Evidence¶

Benedict du Boulay 2015¶

Benedict du Boulay. (2015). Recent Meta-reviews and Meta-analyses of AIED Systems. Int J Artif Intell Educ. https://doi.org/10.1007/s40593-015-0060-1

q2 · i? · review · r2

The letter reports, citing VanLehn (2011), a survey finding that step-based ITSs were "nearly as effective as average human tutors", less effective than expert human tutors, and better than untutored domain content. No effect sizes are printed in the letter.

"VanLehn (2011) found that the effectiveness of the Bstep-based^ intelligent tutoring systems he surveyed were nearly as effective as average human tutors, and that neither of these were as effective as expert human tutors"

Discussion¶

Related Claims¶

• Ma et al. (2014) meta-analysis: step-based ITSs outperformed no tutoring and large-group teacher-led instruction, but showed no differences against small-group or one-to-one human tutoring — related
• One-to-one human tutoring lifts an ordinary student well beyond the average classroom with an effect of about d = 0.79 (VanLehn, 2011, as reported) — related
• Meta-analytic evidence indicates intelligent tutoring systems yield positive learning outcomes compared with non-ITS conditions — a broader claim this one bears on
• ITS substitution: meta-analyses find no significant cognitive learning differences between ITS and human tutoring or small-group instruction — related
• Intelligent tutoring systems can improve learning outcomes, particularly with immediate actionable feedback — a broader claim this one bears on
• A meta-review found intelligent tutoring systems approaching the effectiveness of ordinary human tutors, whose effectiveness is below that of expert tutoring — possibly the same claim (merge candidate)
• Non-expert human tutors follow a limited 5-step collaborative reasoning repertoire, with far more student question-asking than classroom instruction — related
• No significant difference in ICEMS performance scores between AI tutoring and expert instruction — a narrower finding that bears on this claim