Large language models know how the personality of public figures is perceived by the general public

Abstract

We show that people's perceptions of public figures' personalities can be accurately predicted from their names' location in GPT-3's semantic space. We collected Big Five personality perceptions of 226 public figures from 600 human raters. Cross-validated linear regression was used to predict human perceptions from public figures' name embeddings extracted from GPT-3. The models' accuracy ranged from r = .78 to .88 without controls and from r = .53 to .70 when controlling for public figures' likability and demographics, after correcting for attenuation. Prediction models showed high face validity as revealed by the personality-descriptive adjectives occupying their extremes. Our findings reveal that GPT-3 word embeddings capture signals pertaining to individual differences and intimate traits.

Figure 1

The model’s accuracy in predicting public figures’ perceived personality without any controls (green bars) and while controlling for likability and demographics (red bars). Confidence intervals equal 95%. Values in parentheses represent raw accuracy (uncorrected for attenuation). All correlations are significant at the p < .001 level.