Contextual Gated Graph Convolutional Networks for Social Unrest Events Prediction

In a wide range of social unrest events prediction, the dynamic graph convolutional network (DGCN) have been successfully leveraged to achieve reliable performance. The innovation of dynamic graph convolutional networks mainly focuses on capturing the temporal features of unrest events. Inspired by the dynamic graph convolutional network, we propose a new graph convolutional network model called Contextual Gated Graph Convolutional Network (CGGCN). We apply CGGCN to predict and analyze social unrest events. The CGGCN uses the contextual gated layer, which improves the layer-wise propagation rules of graph convolutional networks. The contextual gated layer can re-learn the keyword representation to capture the contextual semantic features of unrest events by using squeeze & excitation module. The principle of the squeeze & excitation module is to increase the weight of meaningful words for event prediction and suppress weaker ones. In this paper, we obtain historical texts including published news and short tweets related to social unrest events. Based on these historical texts data, the CGGCN can predict the occurrence of social unrest events. In addition, we propose a method for establishing the evolution graph of unrest events. In this way, we can use several core words to summarize the evolution of the event. Finally, we design experiments on the specific unrest events data sets. The experimental results show that the CGGCN leads by about 5% - 7% in the performance of prediction compared with other popular methods.