A Survey on Societal Event Forecasting with Deep Learning

TL;DR

This survey reviews how deep learning techniques are applied to forecast societal events like civil unrest and crime, highlighting recent advances, data sources, and future challenges in the field.

Contribution

It provides a comprehensive overview of deep learning methods and data resources used for societal event prediction, focusing on civil unrest and crime.

Findings

Deep learning models have significantly advanced societal event forecasting.

Public data sources like social media and news are crucial for predictions.

Challenges include data quality, model interpretability, and real-time forecasting.

Abstract

Population-level societal events, such as civil unrest and crime, often have a significant impact on our daily life. Forecasting such events is of great importance for decision-making and resource allocation. Event prediction has traditionally been challenging due to the lack of knowledge regarding the true causes and underlying mechanisms of event occurrence. In recent years, research on event forecasting has made significant progress due to two main reasons: (1) the development of machine learning and deep learning algorithms and (2) the accessibility of public data such as social media, news sources, blogs, economic indicators, and other meta-data sources. The explosive growth of data and the remarkable advancement in software/hardware technologies have led to applications of deep learning techniques in societal event studies. This paper is dedicated to providing a systematic and comprehensive overview of deep learning technologies for societal event predictions. We focus on two domains of societal events: \textit{civil unrest} and \textit{crime}. We first introduce how event forecasting problems are formulated as a machine learning prediction task. Then, we summarize data resources, traditional methods, and recent development of deep learning models for these problems. Finally, we discuss the challenges in societal event forecasting and put forward some promising directions for future research.