@inproceedings{xue-etal-2025-towards,
    title = "Towards an Automated Framework to Audit Youth Safety on {T}ik{T}ok",
    author = "Xue, Linda  and
      Corso, Francesco  and
      Fontana, Nicolo  and
      Liu, Geng  and
      Ceri, Stefano  and
      Pierri, Francesco",
    editor = "Blodgett, Su Lin  and
      Curry, Amanda Cercas  and
      Dev, Sunipa  and
      Li, Siyan  and
      Madaio, Michael  and
      Wang, Jack  and
      Wu, Sherry Tongshuang  and
      Xiao, Ziang  and
      Yang, Diyi",
    booktitle = "Proceedings of the Fourth Workshop on Bridging Human-Computer Interaction and Natural Language Processing (HCI+NLP)",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2025.hcinlp-1.9/",
    pages = "113--119",
    ISBN = "979-8-89176-353-1",
    abstract = "This paper investigates the effectiveness of TikTok{'}s enforcement mechanisms for limiting the exposure of harmful content to youth accounts. We collect over 7000 videos, classify them as harmful vs not-harmful, and then simulate interactions using age-specific sockpuppet accounts through both passive and active engagement strategies. We also evaluate the performance of large language (LLMs) and vision-language models (VLMs) in detecting harmful content, identifying key challenges in precision and scalability. Preliminary results show minimal differences in content exposure between adult and youth accounts, raising concerns about the platform{'}s age-based moderation. These findings suggest that the platform needs to strengthen youth safety measures and improve transparency in content moderation."
}