@inproceedings{pham-etal-2025-surveypilot,
    title = "{S}urvey{P}ilot: an Agentic Framework for Automated Human Opinion Collection from Social Media",
    author = "Pham, Viet Thanh  and
      Qu, Lizhen  and
      Li, Zhuang  and
      Sharma, Suraj  and
      Haffari, Gholamreza",
    editor = "Che, Wanxiang  and
      Nabende, Joyce  and
      Shutova, Ekaterina  and
      Pilehvar, Mohammad Taher",
    booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/acl25-workshop-ingestion/2025.acl-long.221/",
    pages = "4397--4422",
    ISBN = "979-8-89176-251-0",
    abstract = "Opinion survey research is a crucial method used by social scientists for understanding societal beliefs and behaviors. Traditional methodologies often entail high costs and limited scalability, while current automated methods such as opinion synthesis exhibit severe biases and lack traceability. In this paper, we introduce SurveyPilot, a novel finite-state orchestrated agentic framework that automates the collection and analysis of human opinions from social media platforms. SurveyPilot addresses the limitations of pioneering approaches by (i) providing transparency and traceability in each state of opinion collection and (ii) incorporating several techniques for mitigating biases, notably with a novel genetic algorithm for improving result diversity. Our extensive experiments reveal that SurveyPilot achieves a close alignment with authentic survey results across multiple domains, observing average relative improvements of 68,98{\%} and 51,37{\%} when comparing to opinion synthesis and agent-based approaches. Implementation of SurveyPilot is available on https://github.com/thanhpv2102/SurveyPilot."
}