CUP_CDLSTM: Civil Unrest Event Prediction Using Convolutional Neural Network, DistilBERT, and Long Short-Term Memory

Civil unrest, a major trouble in the country's progress, requires timely detection and prevention. It causes numerous major issues, including loss of life and injury, resource depletion, political instability, and violations of human rights. Automating the early warning civil unrest event prediction with social media data becomes critically important. Existing baseline methods through text datasets obtained from social media have shown promising results. However, most existing baseline methods are domain-specific and lacking in robustness and generalization. As of now, there has been less work done addressing these issues in civil unrest event prediction. To overcome these limitations, this article presents a novel method as CUP_CDLSTM by combining the convolutional neural network-long short-term memory (CNN-LSTM) model and the pretrained distilBERT model to predict civil unrest event prediction using social media data. First, the proposed CUP_CDLSTM model utilizes the LSTM model to learn temporal features followed by CNN utilized to learn spatial features from the correlation matrix of different features. DistilBERT is utilized to generate weighted word embedding to advance the contextual features. The proposed CUP_CDLSTM model is trained with two datasets of different geographical locations for predicting civil unrest events which include spatial, temporal, and event weights as input features. The proposed CUP_CDLSTM model outperforms the baseline methods by up to 5% on both the Hong Kong protest dataset and the black lives matter (BLM) protest dataset in terms of accuracy. It has shown significantly faster training and inference times than existing baseline models.