Inconsistencies in Classification of Online News Articles: A Call for Common Standards in Brand Safety Services

2026-01-03

arXiv.org

AI Summary

This study addresses significant inconsistencies among brand safety vendors in classifying news content, which lead to misplaced advertisements and revenue loss for publishers. For the first time, it systematically quantifies discrepancies in safety ratings assigned by three leading vendors across 4,352 news articles spanning 51 news domains, revealing substantial conflicts in their classifications. The findings underscore the absence of a unified standard in current brand safety practices, highlighting the adverse impact on the digital advertising ecosystem. The work calls for the establishment of transparent, consistent industry-wide guidelines to mitigate these issues and foster greater reliability in content categorization for advertising purposes.

Technology Category

• Application Domains: Misinformation & Fake News
• Natural Language Processing: Safety and Robustness
• Computer Vision: Bias, Fairness & Privacy

Application Category

• Responsible Web: Mitigating online harms, including harassment, spam, and fake reviews
• Security and Privacy: Large-scale security measurements
• Web Mining and Content Analysis: Web data quality in the era of algorithmically-generated content

Abstract

This study examines inconsistencies in the brand safety classifications of online news articles by analyzing ratings from three leading brand safety providers, DoubleVerify, Integral Ad Science, and Oracle. We focus on news content because of its central role in public discourse and the significant financial consequences of unsafe classifications in a sector that is already underserved by digital ad spending. By collecting data from 4,352 news articles on 51 domains, our analysis shows that brand safety services often produce conflicting classifications, with significant discrepancies between providers. These inconsistencies can have harmful consequences for both advertisers and publishers, leading to misplaced advertising spending and revenue losses. This research provides critical insights into the shortcomings of the current brand safety landscape. We argue for a standardized and transparent brand safety system to mitigate the harmful effects of the current system on the digital advertising ecosystem.

Problem

• brand safety
• classification inconsistency
• online news articles
• digital advertising
• content moderation

Innovation

• brand safety
• classification inconsistency
• online news
• advertising standards
• digital advertising ecosystem