Inferring Human Traits From Facebook Statuses

TL;DR

This paper demonstrates that language models can accurately predict a wide range of human traits from Facebook statuses, providing interpretable insights and analyzing social media-based biases and applications.

Contribution

It introduces a single interpretable model that achieves state-of-the-art results across various human traits from Facebook data, with analysis of influential words and societal implications.

Findings

State-of-the-art prediction of traits like gender, personality, IQ, and political identity.

Published lists of influential words for each trait for hypothesis generation.

Analysis of gender bias and psychographic model usage in social media.

Abstract

This paper explores the use of language models to predict 20 human traits from users' Facebook status updates. The data was collected by the myPersonality project, and includes user statuses along with their personality, gender, political identification, religion, race, satisfaction with life, IQ, self-disclosure, fair-mindedness, and belief in astrology. A single interpretable model meets state of the art results for well-studied tasks such as predicting gender and personality; and sets the standard on other traits such as IQ, sensational interests, political identity, and satisfaction with life. Additionally, highly weighted words are published for each trait. These lists are valuable for creating hypotheses about human behavior, as well as for understanding what information a model is extracting. Using performance and extracted features we analyze models built on social media. The real world problems we explore include gendered classification bias and Cambridge Analytica's use of psychographic models.