@inproceedings{niu-etal-2026-twiusd,
    title = "{T}wi{USD}: A Benchmark Dataset and Structure-Aware {LLM} Framework for User Stance Detection",
    author = "Niu, Fuqiang  and
      Chen, Zini  and
      Xie, Zhiyu  and
      Huang, Hu  and
      Liao, Qing  and
      Wang, Qianlong  and
      Dai, Genan  and
      Zhang, Bowen",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.acl-long.2095/",
    pages = "45198--45212",
    ISBN = "979-8-89176-390-6",
    abstract = "Political user-level stance detection is vital for analyzing polarization, yet progress is hindered by the scarcity of high-quality benchmarks integrating linguistic and social signals. Existing datasets, largely relying on noisy heuristic or distant supervision, limit model robustness and generalizability. To address this, we introduce TwiUSD, a large-scale, expert-annotated benchmark for political user-level stance detection with explicit social network structure. TwiUSD comprises 16,211 users and 47,757 tweets, labeled by domain experts using a protocol that integrates both user content and followee signals, ensuring high-quality annotations (kappa $>$ 0.9). Building upon TwiUSD, we propose MRFG, a Multi-scale Relevance Filtering and Graph-aware framework that leverages large language models to filter stance-relevant followee content and adaptively routes features based on structural informativeness. This design enables robust stance prediction by jointly modeling semantic and relational cues. Extensive experiments show that MRFG significantly outperforms strong baselines, highlighting the importance of relevance filtering and structure-aware modeling."
}