@inproceedings{hoang-etal-2025-hybrid,
    title = "A Hybrid Theory and Data-driven Approach to Persuasion Detection with Large Language Models",
    author = "Hoang, Gia Bao  and
      Ransom, Keith J  and
      Stephens, Rachel  and
      Semmler, Carolyn  and
      Fay, Nicolas  and
      Mitchell, Lewis",
    editor = "Velutharambath, Aswathy  and
      Labat, Sofie  and
      Falk, Neele  and
      Plaza-del-Arco, Flor Miriam  and
      Klinger, Roman  and
      Hoste, V{\'e}ronique",
    booktitle = "Proceedings of the First Workshop on Integrating {NLP} and Psychology to Study Social Interactions ({NLPSI}) @{ICWSM} `25",
    month = jun,
    year = "2025",
    address = "Copenhagen, Denmark",
    publisher = "Association for the Advancement of Artificial Intelligence (www.aaai.org)",
    url = "https://preview.aclanthology.org/ingest-nlpsi/2025.nlpsi-1.5/",
    pages = "45--56",
    abstract = "Traditional psychological models of belief revision focus on face-to-face interactions, but with the rise of social media, more effective models are needed to capture belief revision at scale, in this rich text-based online discourse. Here, we use a hybrid approach, utilizing large language models (LLMs) to develop a model that predicts successful persuasion using features derived from psychological experiments.\par Our approach leverages LLM generated ratings of features previously examined in the literature to build a random forest classification model that predicts whether a message will result in belief change. Of the eight features tested, $\textit{epistemic emotion}$ and $\textit{willingness to share}$ to share were the top-ranking predictors of belief change in the model. Our findings provide insights into the characteristics of persuasive messages and demonstrate how LLMs can enhance models of successful persuasion based on psychological theory. Given these insights, this work has broader applications in fields such as online influence detection and misinformation mitigation, as well as measuring the effectiveness of online narratives."
}