Computational Approach to Detecting and Predicting Occupy Protest Events

Abstract

We introduce a computational approach to detecting and predicting occupy protest events over a daily timeframe. Existing methods mainly solve this problem by document clustering techniques. This paper proposes a novel graph-based occupy protest event detection framework which applies subgraph pattern mining for this task. In addition, we also use a standard linear logistic regression model to estimate the probability of an OPE occurring on a specific day. A wealth of event data about Occupy Wall Street in New York and Occupy Central in Hong Kong from the Global Data on Events, Location, and Tone (GDELT) are utilized in the work. Experimental results on these datasets show that the proposed method can achieve higher detection accuracy with 0.921 on average and MCC value 0.748. The ROC curve shows our prediction model results in very high forecasting precision with accuracy reaching 91.96%, indicating the predictive power of the proposed method.