White Paper -- Objectionable Online Content: What is harmful, to whom, and why

TL;DR

This white paper discusses defining objectionable online content, identifying who it harms, and why, to support research on automated detection methods using a comprehensive video repository.

Contribution

It provides a framework for categorizing harmful content and outlines a strategy for building a large video dataset for automated detection research.

Findings

Defined harmful content categories

Identified target audiences and harm reasons

Proposed a strategy for dataset development

Abstract

This White Paper summarizes the authors' discussion regarding objectionable content for the University of Houston (UH) Research Team to outline a strategy for building an extensive repository of online videos to support research into automated multimodal approaches to detect objectionable content. The workshop focused on defining what harmful content is, to whom it is harmful, and why it is harmful.