Self-reported binary gender prediction from personality traits: Alignment between machine learning importance and classical effect sizes

Heeseung Cho, Yiyu Chen, Christian Wallraven · 2026

Read Self-reported binary gender prediction from personality traits: Alignment between machine learning importance and classical effect sizes by Heeseung Cho, Yiyu Chen, Christian Wallraven (2026) in the Tower of Babel, a free online library of public-domain works preserved in clean, searchable text. No sign-up. The full text is served as a plain-text file at a predictable URL, where text is present: https://antarctic-labs.com/tower-of-babel/plos-pone-0355193.txt.

Description

Heeseung Cho, Yiyu Chen, and Christian Wallraven check in 2026 whether computer rankings of personality traits match older statistical measures of group difference. They trained several learning models in two very large surveys. Each model guessed a person's self reported gender from personality trait scores. Rankings from the models were then compared with classic effect sizes and with combined distance measures.

Rankings stayed stable across many model runs. In one survey they matched simple effect sizes almost perfectly, while in the other they matched only the combined measures well. The split, the authors argue, comes from how traits overlap with each other, not from hidden new patterns in the data.

Catalog record

CREATORHeeseung Cho, Yiyu Chen, Christian Wallraven
YEAR2026
COLLECTIONPAPERS
FORMATTXT
FILE SIZE45882
LICENSECC_BY
RIGHTSCC BY
SOURCEPLOS

Source: https://doi.org/10.1371/journal.pone.0355193

Browse the full library · About the Tower of Babel