Identifying emergency stages in Facebook posts of police departments with convolutional and recurrent neural networks and support vector machines

TL;DR

This paper develops and compares machine learning models, including CNNs, RNNs, and SVMs, to classify Facebook posts from police departments into emergency-related categories, achieving high accuracy with an RNN.

Contribution

It introduces a novel approach combining deep neural networks and word embeddings for classifying police Facebook posts into emergency categories.

Findings

RNN with custom word2vec achieved F1 of 0.839

Deep learning models outperform traditional SVMs

Effective classification aids emergency response efforts

Abstract

Classification of social media posts in emergency response is an important practical problem: accurate classification can help automate processing of such messages and help other responders and the public react to emergencies in a timely fashion. This research focused on classifying Facebook messages of US police departments. Randomly selected 5,000 messages were used to train classifiers that distinguished between four categories of messages: emergency preparedness, response and recovery, as well as general engagement messages. Features were represented with bag-of-words and word2vec, and models were constructed using support vector machines (SVMs) and convolutional (CNNs) and recurrent neural networks (RNNs). The best performing classifier was an RNN with a custom-trained word2vec model to represent features, which achieved the F1 measure of 0.839.