Early Warning Signals of Social Instabilities in Twitter Data
This work addresses the challenge of predicting social instabilities in real-time for policymakers or security agencies, though it appears incremental as it builds on existing methods like BERT and anomaly detection.
The researchers tackled the problem of identifying early warning signals for socially disruptive events like riots and wars using Twitter data, proposing a topological approach combined with BERT models. Their results show that the persistent-gradient method is stable and outperforms deep-learning-based anomaly detection algorithms, with promising generalizability in out-of-sample tasks.
The goal of this project is to create and study novel techniques to identify early warning signals for socially disruptive events, like riots, wars, or revolutions using only publicly available data on social media. Such techniques need to be robust enough to work on real-time data: to achieve this goal we propose a topological approach together with more standard BERT models. Indeed, topology-based algorithms, being provably stable against deformations and noise, seem to work well in low-data regimes. The general idea is to build a binary classifier that predicts if a given tweet is related to a disruptive event or not. The results indicate that the persistent-gradient approach is stable and even more performant than deep-learning-based anomaly detection algorithms. We also benchmark the generalisability of the methodology against out-of-samples tasks, with very promising results.