Figure 2From: Exposing influence campaigns in the age of LLMs: a behavioral-based AI approach to detecting state-sponsored trolls(a) AUC and Accuracy of the LSTM-based sequence classification approach with trajectories composed of state-action pairs or actions only, and (b) Precision, Recall, and F1-Score of the LSTM-based sequence classification approach with trajectories composed of state-action pairs or actions onlyBack to article page