Latent learner profiles did not moderate the effectiveness of the adaptive ITS¶

Claim · All claims
Evidence · 1 study · causal r3 · q3
Currency · newest study 2026 · not yet checked against its sources · not reviewed by a person

Subclaims¶

q3 i? A five-profile latent profile solution based on prior knowledge, conscientiousness, interest, and academic self-concept produced no significant condition × profile interactions on posttest performance, mental effort, subjective difficulty, or enjoyment. → Sibley 2026

Evidence¶

Sibley 2026¶

Sibley, L., Berner, T., & Schmalfeldt, T. (2026). Effectiveness of adaptive versus non-adaptive intelligent tutoring systems in early primary mathematics. Computers and Education Open 11. https://doi.org/10.1016/j.caeo.2026.100420

q3 · i? · causal · r3

Exploratory latent profile analysis (BIC-supported five-profile solution) followed by regression of posttest performance on condition and profile in the N = 132 experiment. The article reports the printed β, p, and η²p values; no standardized effect size for the interactions is printed, so impact is null.

"The main effect of condition was not significant (β = −0.22, p = .511, η²p = .00), and no significant interaction effects between condition and profile were observed (ps ≥ .198, η²p = .02), indicating that the profiles did not moderate the effectiveness of the adaptive ITS system."

Discussion¶

Related Claims¶

• Intelligent tutoring systems improve achievement over non-individualised instruction — the general claim this finding bears on, with the studies behind it

• Learning Styles Matching Does Not Improve Learning — the general claim this finding bears on, with the studies behind it

• Adaptive versus non-adaptive ITS condition showed no significant differences in mental effort, subjective difficulty, or enjoyment — related
• Conscientiousness exploratorily moderated the effect of ITS condition on subjective difficulty and enjoyment — reports the opposite
• Three latent profiles of psychological adaptation to AI-assisted Japanese learning (maladaptive, moderate, positive) are identified at each of three waves — related
• Three academic self-efficacy profiles (low, moderate, high) are identified among university students with motor disabilities using Latent Profile Analysis — related
• Latent profile analysis identifies three career adapt-abilities subgroups (low, moderate, high) among English majors — related
• Latent profile analysis of pre-service teachers' CT skills identifies three profiles (Novice, Developing, Proficient), revealing heterogeneous, non-linear skill acquisition — related
• Profile sizes: 29.4% low, 41.2% moderate, and 29.4% high academic self-efficacy among students with motor disabilities — related
• Latent profile analysis of combined SR and OB factors identifies six distinct teacher profiles spanning overestimation, underestimation, and alignment — related
• Latent career adapt-abilities profiles differ strongly in core self-evaluations, with a stepwise increase across low, moderate, and high groups — related
• Adaptive task difficulty in an ITS did not improve second-graders' mathematics posttest performance compared with an identical non-adaptive ITS — related
• Latent profile analysis identifies three learner profiles differing in cognitive factors, self-concept, and extraneous load, with significant performance differences — related
• Students' domain-specific self-concept moderates non-interactive teaching: low self-concept students profit, high self-concept students do not — related
• Prior knowledge moderates non-interactive teaching: low conceptual knowledge learners profit more, but very low-knowledge learners may not benefit at all — related