Towards Detecting Harmful Agendas in News Articles

TL;DR

This paper introduces a new task for detecting harmful agendas in news articles, emphasizing interpretability and providing a dataset to advance research in identifying potentially harmful news campaigns.

Contribution

It proposes the novel task of harmful agenda detection, releases the NewsAgendas dataset, and demonstrates effective interpretable models that match black-box performance.

Findings

Interpretable models perform comparably to black-box models.

The NewsAgendas dataset enables research on harmful agenda detection.

Detecting harmful agendas is crucial for mitigating real-world harm from news.

Abstract

Manipulated news online is a growing problem which necessitates the use of automated systems to curtail its spread. We argue that while misinformation and disinformation detection have been studied, there has been a lack of investment in the important open challenge of detecting harmful agendas in news articles; identifying harmful agendas is critical to flag news campaigns with the greatest potential for real world harm. Moreover, due to real concerns around censorship, harmful agenda detectors must be interpretable to be effective. In this work, we propose this new task and release a dataset, NewsAgendas, of annotated news articles for agenda identification. We show how interpretable systems can be effective on this task and demonstrate that they can perform comparably to black-box models.