This repo contains the code related to our participation to the CLEF 2019 Lab ProtestNews shared task.

This notebook describes our participation to the Protest-New Lab, identifying protest events in news articles in English. Systemsare challenged to perform unsupervised domain adaptation against threesub-tasks: document classification, sentence classification, and event ex-traction. We describe the final submitted systems for all sub-tasks, aswell as a series of negative results. Results indicate pretty robust perfor-mances in all tasks (average F1 of 0.705 for the document classificationsub-task, average F1 of 0.592 for the sentence classification sub-task; av-erage F1 0.528 for the event extraction sub-task), ranking in the top 4systems, although drops in the out-of-domain test sets are not minimal.

2019 has been characterized by worldwide waves of protests. Each country’s protests is different but there appear to be common factors. In this paper we present two approaches for identifying protest events in news in English. Our goal is to provide political science and discourse analysis scholars with tools that may facilitate the understanding of this on-going phenomenon. We test our approaches against the ProtestNews Lab 2019 benchmark that challenges systems to perform unsupervised domain adaptation on protest events on three sub-tasks: document classification, sentence classification, and event extraction. Results indicate that developing dedicated architectures and models for each task outperforms simpler solutions based on the propagation of labels from lexical items to documents. Furthermore, we complete the description of our systems with a detailed data analysis to shed light on the limits of the methods.

An old version of code and trained models is available here.