Learning Evolutionary Stages with Hidden Semi-Markov Model for Predicting Social Unrest Events

Social unrest events are common happenings in modern society which need to be proactively handled. An effective method is to continuously assess the risk of upcoming social unrest events and predict the likelihood of these events. Our previous work built a hidden Markov model- (HMM-) based framework to predict indicators associated with country instability, leaving two shortcomings which can be optimized: omitting event participants’ interaction and implicitly learning the state residence time. Inspired by this, we propose a new prediction framework in this paper, using frequent subgraph patterns and hidden semi-Markov models (HSMMs). The feature called BoEAG (Bag-of-Event-Association-subGraph) is constructed based on frequent subgraph mining and the bag of word model. The new framework leverages the large-scale digital history events captured from GDELT (Global Data on Events, Location, and Tone) to characterize the transitional process of the social unrest events’ evolutionary stages, uncovering the underlying event development mechanics and formulating the social unrest event prediction as a sequence classification problem based on Bayes decision. Experimental results with data from five main countries in Southeast Asia demonstrate the effectiveness of the new method, which outperforms the traditional HMM by 5.3% to 16.8% and the logistic regression by 11.2% to 43.6%.

[1]  Jieping Ye,et al.  Feature Constrained Multi-Task Learning Models for Spatiotemporal Event Forecasting , 2017, IEEE Transactions on Knowledge and Data Engineering.

[2]  A. Maruotti,et al.  Hidden Markov and Semi-Markov Models with Multivariate Leptokurtic-Normal Components for Robust Modeling of Daily Returns Series , 2018, Journal of Financial Econometrics.

[3]  Ming Dong,et al.  Equipment health diagnosis and prognosis using hidden semi-Markov models , 2006 .

[4]  Matthew S. Gerber,et al.  Forecasting Civil Unrest Using Social Media and Protest Participation Theory , 2018, IEEE Transactions on Computational Social Systems.

[5]  Fengcai Qiao,et al.  Predicting Social Unrest Events with Hidden Markov Models Using GDELT , 2017 .

[6]  Liang Zhao,et al.  Efficient Learning with Exponentially-Many Conjunctive Precursors to Forecast Spatial Events , 2019 .

[7]  Manjur Ahmed,et al.  AN ONLINE FRAMEWORK FOR CIVIL UNREST PREDICTION USING TWEET STREAM BASED ON TWEET WEIGHT AND EVENT DIFFUSION , 2020 .

[8]  Jiejun Xu,et al.  Using publicly visible social media to build detailed forecasts of civil unrest , 2014, Security Informatics.

[9]  Lawrence R. Rabiner,et al.  A tutorial on hidden Markov models and selected applications in speech recognition , 1989, Proc. IEEE.

[10]  J. Jenkins,et al.  Mapping Mass Political Conflict and Civil Society , 1997 .

[11]  Argimiro Arratia,et al.  Forecasting with twitter data , 2013, ACM Trans. Intell. Syst. Technol..

[12]  Jin Liu,et al.  Prediction of collective actions using deep neural network and species competition model on social media , 2018, World Wide Web.

[13]  Hui Wang,et al.  A Parallel Approach for Frequent Subgraph Mining in a Single Large Graph Using Spark , 2018 .

[14]  Yann Guédon,et al.  Explicit state occupancy modelling by hidden semi-Markov models: application of Derin's scheme , 1990 .

[15]  Johan Bollen,et al.  Twitter mood predicts the stock market , 2010, J. Comput. Sci..

[16]  Jose Cadena,et al.  Forecasting Social Unrest Using Activity Cascades , 2015, PloS one.

[17]  L. Baum,et al.  Statistical Inference for Probabilistic Functions of Finite State Markov Chains , 1966 .

[18]  Sean P. O'Brien,et al.  Crisis Early Warning and Decision Support: Contemporary Approaches and Thoughts on Future Research , 2010 .

[19]  E. Azar The Conflict and Peace Data Bank (COPDAB) Project , 1980 .

[20]  Jan Bulla,et al.  Stylized facts of financial time series and hidden semi-Markov models , 2006, Comput. Stat. Data Anal..