{
  "abstract": "Online debate platforms offer a window into whether exposure to diverse crowds changes how people reason: they capture political preferences, the perceived quality of arguments, and the ideological diversity of the audience. Drawing on theories of deliberative democracy and cross-cutting exposure, I develop a Bayesian logistic regression model that decomposes voting behaviour in online debates into three components: conviction (agreement between a user's prior beliefs and a debate's stance), persuasiveness (perceived argument quality), and cross-cutting exposure (the ideological diversity of a debate's prior voters). I apply this framework to the DDO dataset: approximately 341k votes across 78k debates on 48 socio-political topics. As the platform provides no predefined topic labels, I infer topic and stance from debate text using large language models. I test whether a more ideologically diverse prior audience weakens a voter's conviction, a central claim from the cross-cutting exposure literature. Persuasiveness is the strongest and most consistent predictor of vote choice, never outweighed by conviction, though conviction remains a credible predictor on several topics tied to personal freedoms. Cross-cutting exposure moderates conviction on 4 of 47 topics, though these results are sensitive to topic classification and sparse coverage, with implications for the design of deliberative platforms.",
  "abstract_shown": true,
  "affiliations": [],
  "article_type": null,
  "arxiv": "2606.03786",
  "author_total": 1,
  "authors": [
    {
      "name": "Elena Candellone"
    }
  ],
  "bibtex": "https://research.draconitic.com/paper/2t5stkzkj2ysy.bib",
  "cited_by": 0,
  "doi": "10.48550/arxiv.2606.03786",
  "fulltext_url": null,
  "id": "2t5stkzkj2ysy",
  "issns": [],
  "landing_url": "https://arxiv.org/abs/2606.03786",
  "language": null,
  "licence": "CC-BY-NC-ND-4.0",
  "licence_label": "CC BY-NC-ND 4.0",
  "licence_source": "article",
  "licence_url": "http://creativecommons.org/licenses/by-nc-nd/4.0/",
  "metadata_licence": "CC0-1.0",
  "native_subjects": [
    [
      "arxiv",
      "physics.soc-ph"
    ],
    [
      "arxiv",
      "stat.ME"
    ],
    [
      "openalex",
      "3315|Social Media and Politics"
    ]
  ],
  "openalex": "W7163391439",
  "pdf_url": "https://arxiv.org/pdf/2606.03786",
  "pmcid": null,
  "pmid": null,
  "published": "2026-09-15",
  "publisher": null,
  "ris": "https://research.draconitic.com/paper/2t5stkzkj2ysy.ris",
  "sources": [
    {
      "first_seen": "2026-10-30T12:21:41Z",
      "native_id": "2606.03786",
      "source": "arxiv",
      "url": "https://arxiv.org/abs/2606.03786"
    }
  ],
  "subjects": [
    {
      "field": "mathematics",
      "origin": "arxiv:stat.ME",
      "subfield": "statistics"
    },
    {
      "field": "physics",
      "origin": "arxiv:physics.soc-ph",
      "subfield": "statistical-nonlinear"
    }
  ],
  "title": "Conviction, persuasiveness, and cross-cutting exposure: a Bayesian model of voting behaviour in online political debates",
  "title_text": "Conviction, persuasiveness, and cross-cutting exposure: a Bayesian model of voting behaviour in online political debates",
  "type": "preprint",
  "updated_at": "2026-10-30T12:21:51Z",
  "url": "https://research.draconitic.com/paper/2t5stkzkj2ysy",
  "venue": "arXiv",
  "versions": []
}