From Notepad AI to Social Media: How Can Text Style Transformation Mitigate Social Harm?

TL;DR

This paper introduces a stylistic text transformation framework inspired by Notepad AI to reduce societal harm on social media by softening harmful comments without censoring content.

Contribution

It proposes a novel approach for mitigating social harm through controlled stylistic rewriting, introducing the Emotion Drift Index (EDI) for evaluation.

Findings

The framework effectively reduces emotional intensity in harmful comments.

The Emotion Drift Index (EDI) quantifies emotional change systematically.

Stylistic transformation preserves core content while decreasing toxicity.

Abstract

The rapid proliferation of harmful and emotionally damaging content on social media platforms has intensified concerns regarding societal harm. While content moderation efforts primarily focus on detecting and removing harmful posts, less attention has been given to mitigating harm through stylistic text transformation while preserving semantic meaning. In this paper, we propose a writing-assistance framework that can reduce societal harm by transforming aggressive, toxic, or emotionally harmful comments into softer, more neutral stylistic forms inspired by Notepad AI, a simple AI writing assistant. Rather than censoring or suppressing speech, we apply controlled stylistic modifications to preserve core informational content while reducing emotional intensity and identity-based attacks. We introduce an Emotion Drift Index (EDI) metric to systematically quantify emotional change and evaluate the effectiveness of stylistic rewriting, thereby reducing harmful interactions in online environments.