Take the Power Back: Screen-Based Personal Moderation Against Hate Speech on Instagram

2026-03-01

AI Summary

This study addresses the widespread lack of personalized adaptation in hate speech moderation mechanisms across different interface contexts on social media platforms. Through a three-round Delphi study involving 40 activists who have experienced online hate speech, the research systematically investigates user preferences for customizable moderation tools across distinct Instagram interfaces—such as comments, Reels, and the main feed. Integrating quantitative ratings, rankings, and qualitative feedback, the analysis focuses on dimensions including input modality, content type, and degree of automation. The findings reveal, for the first time, divergent user preferences between conversational and algorithmically recommended interface contexts. Emphasizing the importance of cross-screen reversibility and user oversight, the study concludes with user-centered design recommendations for personalized content moderation systems.

Technology Category

• Humans and AI: Intelligent User Interfaces
• Application Domains: Humanities & Computational Social Science
• Machine Learning: Learning Preferences or Rankings

Application Category

• User Modeling, Personalization and Recommendation: Social recommender systems and personalization for the social Web
• Economics, Online Markets and Human Computation: Economics and fairness of platforms and recommendation systems
• Social Networks and Social Media: Media and governance, opinion dynamics, filter bubbles, polarization

Abstract

Hate speech remains a pressing challenge on social media, where platform moderation often fails to protect targeted users. Personal moderation tools that let users decide how content is filtered can address some of these shortcomings. However, it remains an open question on which screens (e.g., the comments, the reels tab, or the home feed) users want personal moderation and which features they value most. To address these gaps, we conducted a three-wave Delphi study with 40 activists who experienced hate speech. We combined quantitative ratings and rankings with open questions about required features. Participants prioritized personal moderation for conversational and algorithmically curated screens. They valued features allowing for reversibility and oversight across screens, while input-based, content-type specific, and highly automated features are more screen specific. We discuss the importance of personal moderation and offer user-centered design recommendations for personal moderation on Instagram.

Problem

• hate speech
• personal moderation
• social media
• Instagram
• user-centered design

Innovation

• personal moderation
• hate speech
• Delphi study
• user-centered design
• Instagram