Graph Language Model (GLM): A new graph-based approach to detect social instabilities

This scientific report presents a novel methodology for the early prediction of important political events using News datasets. The methodology leverages natural language processing, graph theory, clique analysis, and semantic relationships to uncover hidden predictive signals within the data. Initially, we designed a preliminary version of the method and tested it on a few events. This analysis revealed limitations in the initial research phase. We then enhanced the model in two key ways: first, we added a filtration step to only consider politically relevant news before further processing; second, we adjusted the input features to make the alert system more sensitive to significant spikes in the data. After finalizing the improved methodology, we tested it on eleven events including US protests, the Ukraine war, and French protests. Results demonstrate the superiority of our approach compared to baseline methods. Through targeted refinements, our model can now provide earlier and more accurate predictions of major political events based on subtle patterns in news data.

Early Warning Signals of Social Instabilities in Twitter Data

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.