Content Fuzzing for Escaping Information Cocoons on Digital Social Media

TL;DR

ContentFuzz is a framework that rewrites social media posts to promote exposure to diverse viewpoints by altering stance labels while preserving original meaning, thus helping escape information cocoons.

Contribution

It introduces a confidence-guided LLM-based fuzzing method to generate meaning-preserving post rewrites that alter stance detection outcomes.

Findings

Effectively changes stance labels across multiple models and datasets.

Maintains semantic integrity of original posts.

Works in multiple languages.

Abstract

Information cocoons on social media limit users' exposure to posts with diverse viewpoints. Modern platforms use stance detection as an important signal in recommendation and ranking pipelines, which can route posts primarily to like-minded audiences and reduce cross-cutting exposure. This restricts the reach of dissenting opinions and hinders constructive discourse. We take the creator's perspective and investigate how content can be revised to reach beyond existing affinity clusters. We present ContentFuzz, a confidence-guided fuzzing framework that rewrites posts while preserving their human-interpreted intent and induces different machine-inferred stance labels. ContentFuzz aims to route posts beyond their original cocoons. Our method guides a large language model (LLM) to generate meaning-preserving rewrites using confidence feedback from stance detection models. Evaluated on four representative stance detection models across three datasets in two languages, ContentFuzz effectively changes machine-classified stance labels, while maintaining semantic integrity with respect to the original content.