Text-generation meta-analysis (Educational Psychology Review 2023) — Hedges g ≈ .41; LARGEST for 301-600 word texts; NO EFFECT beyond ~900 words
Created 2026-06-20
Summary
Claim: Text-generation meta-analysis (Educational Psychology Review 2023): Hedges g ≈ .41, not attributable to time-on-task; largest for 301-600 word texts and NO effect beyond ~900 words.
Source: Educational Psychology Review (2023).
Confidence: Verified (meta-analysis).
Caveat: Length ceiling is the critical practical limit.
Why this matters for Candid: Counsel against very-long-form input tools — the generation effect ceilings beyond ~900 words. Practical implication: keep input fields short and focused; if a tool needs many inputs, break into screens (also supports R2 — Design every multi-step tool for the goal gradient: visible progress + low interaction cost + start-state non-empty when possible from Brief E).
Related entries
Referenced by (3)
- research-notes Research notes (capture-layer top-up): why interactive online tools are psychologically engaging — six additional mechanisms (June 2026) relates-to
- reference Caveats for the engagement-mechanisms top-up: strong independent evidence sits at the MECHANISM level not the business-outcome level; nearly every effect is moderated relates-to
- rule R4 — Where appropriate, make the user GENERATE inputs (not just pick from menus) — the generation effect d≈0.40 is real but ceilings beyond ~900 words and doesn't scale to expository text depends-on