Pachinko Prediction: A Bayesian method for event prediction from social media data

作者：

Highlights：

• An empirical Bayesian approach for making probabilistic predictions of events such as social unrest from online social network data.

• A framework for predictive modelling from social networks by combining machine learning tools.

• Analysis of datasets relating to social unrest in Australia during 2017/18, including a dataset used to classify protest-relevant tweets included with the paper.

摘要

•An empirical Bayesian approach for making probabilistic predictions of events such as social unrest from online social network data.•A framework for predictive modelling from social networks by combining machine learning tools.•Analysis of datasets relating to social unrest in Australia during 2017/18, including a dataset used to classify protest-relevant tweets included with the paper.

论文关键词：Bayesian statistics,Social unrest,Machine learning,Prediction

论文评审过程：Received 22 September 2018, Revised 27 September 2019, Accepted 14 October 2019, Available online 20 November 2019, Version of Record 13 January 2020.

论文官网地址：https://doi.org/10.1016/j.ipm.2019.102147