AIGENIE: LLM-powered psychological scale development tutorial accepted at Behavior Research Methods
GolinoHudson · x · 2026-11-15
The tutorial paper on AIGENIE (R package implementing the AI-GENIE framework) has been accepted at Behavior Research Methods. It uses LLMs to generate candidate scale items, converts them to embeddings, and applies a multi-step reduction pipeline — Exploratory Graph Analysis, Unique Variable Analysis, bootstrap EGA — to produce structurally validated item pools entirely in silico, replacing much of the expert iteration and piloting in traditional scale development. Eight tutorial sections cover setup through fully local operation, with Big Five and AI Anxiety as running examples.
More from Research
- Ceci n'est pas le benzène: how chemical representations mislead ML in drug discovery — CatAstro_Piyush · 2026-11-16
- Science Prediction Universe benchmark: best agents score just 0.486 at predicting wet-lab outcomes — liangchen5518 · 2026-11-16
- Expected Value framework: turning ML predictions into measurable ROI — mdancho84 · 2026-11-16
- ML predictions as probabilities: the foundation for business data science — mdancho84 · 2026-11-16
- mdancho84 kicks off a series on 'Data Science for Business' by Provost & Fawcett — mdancho84 · 2026-11-16
- 9 fake software brands, 18 queries to ChatGPT and Google AI Mode: zero hallucinations — raja314 · 2026-11-16