Multitask Models for Supervised Protests Detection in Texts

TL;DR

This paper explores the use of multitask neural networks to improve the detection of political protests in news texts by simultaneously performing article classification, sentence detection, and event extraction.

Contribution

It introduces a multitask learning framework that leverages shared features across related tasks to enhance protest detection performance.

Findings

Achieved performance near or above state-of-the-art in protest detection

Multitask models effectively learn shared features from multiple tasks

Demonstrated potential for improved political event coding

Abstract

The CLEF 2019 ProtestNews Lab tasks participants to identify text relating to political protests within larger corpora of news data. Three tasks include article classification, sentence detection, and event extraction. I apply multitask neural networks capable of producing predictions for two and three of these tasks simultaneously. The multitask framework allows the model to learn relevant features from the training data of all three tasks. This paper demonstrates performance near or above the reported state-of-the-art for automated political event coding though noted differences in research design make direct comparisons difficult.