@inproceedings{petrova-etal-2026-much,
    title = "How Much Does Persuasion Strategy Matter? {LLM}-Annotated Evidence from Charitable Donation Dialogues",
    author = "Petrova, Tatiana  and
      Sokol, Stanislav  and
      State, Radu",
    editor = "Stranisci, Marco Antonio  and
      Falk, Neele  and
      Labat, Sofie  and
      Lo, Soda Marem  and
      Velutharambath, Aswathy  and
      Weber, Sabine  and
      Damiano, Rossana  and
      Frenda, Simona  and
      Hoste, Veronique  and
      Kleinberg, Bennett  and
      Klinger, Roman  and
      Patti, Viviana  and
      Plaza-del-Arco, Flor Miriam  and
      Sap, Maarten  and
      Yimam, Seid Muhie",
    booktitle = "Proceedings of the 1st Workshop on Social Context ({S}o{C}on) and the 2nd Workshop on Integrating {NLP} and Psychology to Study Social Interactions ({NLPSI}) @ {LREC} 2026",
    month = may,
    year = "2026",
    address = "Palma, Mallorca (Spain)",
    publisher = "European Language Resources Association (ELRA)",
    url = "https://preview.aclanthology.org/revision-workflow/2026.socon-1.5/",
    doi = "10.63317/4hquav3a9b4n",
    pages = "40--47",
    abstract = "Which persuasion strategies, if any, are associated with donation compliance? Answering this requires fine-grained strategy labels across a full corpus and statistical tests corrected for multiple comparisons. We annotate all 10,600 persuader turns in the 1,017-dialogue PersuasionForGood corpus with a taxonomy of 41 strategies in 11 categories, using three open-source large language models (Qwen3:30b, Mistral-Small-3.2, Phi-4). Strategy categories alone explain little variance in donation outcome (pseudo R-squared approximately 0.015, consistent across all three annotators). Guilt Induction is the only strategy significantly associated with lower donation rates (approximately -23 percentage points), an effect that replicates across all three models despite only moderate inter-model agreement. Reciprocity is the most robust positive correlate. Target sentiment and interest predict whether a donation occurs but show at most a weak correlation with donation amount. Logistic regression with sentiment, interest, Guilt Induction, and Reciprocity achieves nearly the same fit (pseudo R-squared = 0.080) as the full model with all strategy categories. These findings suggest that strategy identification alone is insufficient to explain persuasion effectiveness, and that guilt-based appeals may be counterproductive in prosocial settings. We release the fully annotated corpus as a public resource."
}