HumVI: A Multilingual Dataset for Detecting Violent Incidents Impacting Humanitarian Aid

TL;DR

HumVI is a multilingual dataset of news articles about violent incidents impacting humanitarian aid, designed to support NLP classification tasks and improve data-driven decision-making in humanitarian contexts.

Contribution

The paper introduces HumVI, a novel multilingual dataset with expert-verified labels, and provides benchmarks using advanced deep learning techniques for violent incident detection.

Findings

Dataset includes English, French, Arabic articles on violent incidents.

Multiple deep learning benchmarks demonstrate effective classification performance.

The dataset is publicly available for further research and development.

Abstract

Humanitarian organizations can enhance their effectiveness by analyzing data to discover trends, gather aggregated insights, manage their security risks, support decision-making, and inform advocacy and funding proposals. However, data about violent incidents with direct impact and relevance for humanitarian aid operations is not readily available. An automatic data collection and NLP-backed classification framework aligned with humanitarian perspectives can help bridge this gap. In this paper, we present HumVI - a dataset comprising news articles in three languages (English, French, Arabic) containing instances of different types of violent incidents categorized by the humanitarian sector they impact, e.g., aid security, education, food security, health, and protection. Reliable labels were obtained for the dataset by partnering with a data-backed humanitarian organization, Insecurity Insight. We provide multiple benchmarks for the dataset, employing various deep learning architectures and techniques, including data augmentation and mask loss, to address different task-related challenges, e.g., domain expansion. The dataset is publicly available at https://github.com/dataminr-ai/humvi-dataset.