@inproceedings{susanto-etal-2025-multi,
    title = "A Multi-Labeled Dataset for {I}ndonesian Discourse: Examining Toxicity, Polarization, and Demographics Information",
    author = "Susanto, Lucky  and
      Wijanarko, Musa Izzanardi  and
      Pratama, Prasetia Anugrah  and
      Tang, Zilu  and
      Akyas, Fariz  and
      Hong, Traci  and
      Idris, Ika Karlina  and
      Aji, Alham Fikri  and
      Wijaya, Derry Tanti",
    editor = "Che, Wanxiang  and
      Nabende, Joyce  and
      Shutova, Ekaterina  and
      Pilehvar, Mohammad Taher",
    booktitle = "Findings of the Association for Computational Linguistics: ACL 2025",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingestion-acl-25/2025.findings-acl.966/",
    pages = "18863--18890",
    ISBN = "979-8-89176-256-5",
    abstract = "Online discourse is increasingly trapped in a vicious cycle where polarizing language fuelstoxicity and vice versa. Identity, one of the most divisive issues in modern politics, oftenincreases polarization. Yet, prior NLP research has mostly treated toxicity and polarization asseparate problems. In Indonesia, the world{'}s third-largest democracy, this dynamic threatens democratic discourse, particularly in online spaces. We argue that polarization and toxicity must be studied in relation to each other. To this end, we present a novel multi-label Indonesian dataset annotated for toxicity, polarization, and annotator demographic information. Benchmarking with BERT-base models and large language models (LLMs) reveals that polarization cues improve toxicity classification and vice versa. Including demographic context further enhances polarization classification performance."
}