Social Media Unrest Prediction during the {COVID}-19 Pandemic: Neural Implicit Motive Pattern Recognition as Psychometric Signs of Severe Crises

TL;DR

This paper develops and validates NLP-based psychometric models to predict social unrest during COVID-19 by analyzing social media language, revealing increased conflict potential and demonstrating the method's effectiveness for psychological research.

Contribution

It introduces scalable, automated psychometric predictors for social unrest based on social media data, advancing the state of the art in crisis prediction during pandemics.

Findings

Significant increase in conflict psychometrics during COVID-19

Validated models replicate and predict social unrest indicators

Demonstrated applicability of NLP for psychological analysis

Abstract

The COVID-19 pandemic has caused international social tension and unrest. Besides the crisis itself, there are growing signs of rising conflict potential of societies around the world. Indicators of global mood changes are hard to detect and direct questionnaires suffer from social desirability biases. However, so-called implicit methods can reveal humans intrinsic desires from e.g. social media texts. We present psychologically validated social unrest predictors and replicate scalable and automated predictions, setting a new state of the art on a recent German shared task dataset. We employ this model to investigate a change of language towards social unrest during the COVID-19 pandemic by comparing established psychological predictors on samples of tweets from spring 2019 with spring 2020. The results show a significant increase of the conflict indicating psychometrics. With this work, we demonstrate the applicability of automated NLP-based approaches to quantitative psychological research.