Auditing Exposure to Harmful Content on TikTok using Multimodal Language Models: A Cross-National, Age-Stratified Study
Online video platforms can expose young users to harmful content, but independent audits remain difficult because video annotation is costly and moderation judgments vary across languages. We audit TikTok in France, Italy, and Sweden with sockpuppet accounts representing four age personas (13, 16, 19, 40), collecting 36,971 videos from passive For-You-page scrolling and active sessions that scroll, search for harm keywords, and scroll again. To scale annotation, we validate four multimodal LLMs against native-speaker labels on a 300-video reference set. Gemini 2.5 Flash with eight sampled frames plus text performs best (aggregate kappa = 0.42), at half the per-call cost of native-video upload, and we apply it to a 10% sample for approximately \$50 in total API spend across both modalities. Keyword search returns 35-56% harmful content, a 1.5-7.5x increase over the scrolling baseline in ten of twelve country-age combinations; the spike is temporary and flattens the age differences observed in France and Sweden. Under passive scrolling, Italy has the highest harm rate at every age, with Italian age-19 reaching 48.6%. Overall, MLLM-based auditing offers a scalable approach for cross-national youth-safety audits, while provider safety filters (1.1% refusal rate) under-count the most explicit harms.
Code (0)
등록된 구현이 없습니다.
Similar Papers 제목 키워드 기반
AutoLike: Auditing Social Media Recommendations through User Interactions
Modern social media platforms, such as TikTok, Facebook, and YouTube, rely on recommendation systems to personalize content for users based on user interactions with endless streams of content, such as "For You" pages. H…
Recommendation SystemsMTikGuard System: A Transformer-Based Multimodal System for Child-Safe Content Moderation on TikTok
With the rapid rise of short-form videos, TikTok has become one of the most influential platforms among children and teenagers, but also a source of harmful content that can affect their perception and behavior. Such con…
BigTokDetect: A Clinically-Informed Vision-Language Modeling Framework for Detecting Pro-Bigorexia Videos on TikTok
Social media platforms face escalating challenges in detecting harmful content that promotes muscle dysmorphic behaviors and cognitions (bigorexia). This content can evade moderation by camouflaging as legitimate fitness…
Hate in the Time of Algorithms: Evidence on Online Behavior from a Large-Scale Experiment
Social media algorithms are thought to amplify variation in user beliefs, thus contributing to radicalization. However, quantitative evidence on how algorithms and user preferences jointly shape harmful online engagement…
Harm in AI-Driven Societies: An Audit of Toxicity Adoption on Chirper.ai
Large Language Models (LLMs) are increasingly embedded in autonomous agents that engage, converse, and co-evolve in online social platforms. While prior work has documented the generation of toxic content by LLMs, far le…