{"slug": "agentic-detection-of-online-conspiracies", "title": "Agentic Detection of Online Conspiracies", "summary": "A September 24, 2026 arXiv paper proposes an agentic framework that uses social-context tools to detect conspiracy discourse in online posts by inferring a speaker's intent rather than relying on explicit claims or lexical markers. Tested on a Hebrew Twitter dataset covering 80%–90% of public Hebrew tweets from late 2018 to early 2023, including several election cycles and the COVID pandemic and vaccination campaigns, the context-aware agentic framework outperformed text-only classification and a non-agentic model given the same contexts, according to the authors. The paper also analyzes errors and token-economy efficiency tradeoffs, concluding that conspiracy detection is a socially embedded interpretation task requiring per-case adaptive reasoning.", "body_md": "# Computer Science > Computation and Language\n\n  [Submitted on 24 Sep 2026]\n\n# Title:Agentic Detection of Online Conspiracies\n\n[View PDF](http://arxiv.org/pdf/2609.30250v1)\n\n[HTML (experimental)](https://arxiv.org/html/2609.30250v1)\n\nAbstract:Conspiratorial discourse on social media is not always expressed through explicit claims or stable lexical markers. The same surface content may express endorsement, legitimate concerns, criticism, satire, or mockery. The main challenge is therefore not only recognizing conspiracy-related claims, but inferring the speaker's intent -- the utterance's illocutionary force. We argue that this can be achieved through the use of relevant social contexts and propose an agentic framework, equipped with a set of tools supporting social queries.\n\nWe demonstrate the benefits of our approach on a unique dataset of Hebrew tweets, covering 80\\%--90\\% of the public Hebrew tweets published over a four-year span (late 2018-- early 2023), encompassing several election cycles as well as the COVID pandemic years and related vaccination campaigns. This extensive coverage can be used in recovering different social contexts. Evaluating our framework on a manually-annotated adversarial dataset, we find that context-aware workflows consistently outperform text-only classification and that the agentic framework performs significantly better than other frameworks and settings, including a non-agentic model exposed to the same contexts available to the agent. We further provide an analysis of the results, the errors and efficiency (token economy) tradeoffs.\n\nThese findings support viewing the task of conspiracy detection as a socially embedded interpretation task, in which effective classification depends not only on access to contexts, but also on adaptive reasoning in which the agent uses tools on a per-case basis, asking only for evidence relevant to its current reasoning step.\n\n### References & Citations\n\nLoading...\n\n# Bibliographic and Citation Tools\n\nBibliographic Explorer \n\n*(*[What is the Explorer?](https://info.arxiv.org/labs/showcase.html#arxiv-bibliographic-explorer))\nConnected Papers \n\n*(*[What is Connected Papers?](https://www.connectedpapers.com/about))\nLitmaps \n\n*(*[What is Litmaps?](https://www.litmaps.co/))\nscite Smart Citations \n\n*(*[What are Smart Citations?](https://www.scite.ai/))\n# Code, Data and Media Associated with this Article\n\nalphaXiv \n\n*(*[What is alphaXiv?](https://alphaxiv.org/))\nCatalyzeX Code Finder for Papers \n\n*(*[What is CatalyzeX?](https://www.catalyzex.com))\nDagsHub \n\n*(*[What is DagsHub?](https://dagshub.com/))\nGotit.pub \n\n*(*[What is GotitPub?](http://gotit.pub/faq))\nHugging Face \n\n*(*[What is Huggingface?](https://huggingface.co/huggingface))\nScienceCast \n\n*(*[What is ScienceCast?](https://sciencecast.org/welcome))\n# Demos\n\n# Recommenders and Search Tools\n\nInfluence Flower \n\n*(*[What are Influence Flowers?](https://influencemap.cmlab.dev/))\nCORE Recommender \n\n*(*[What is CORE?](https://core.ac.uk/services/recommender))\n# arXivLabs: experimental projects with community collaborators\n\narXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.\n\nBoth individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.\n\nHave an idea for a project that will add value for arXiv's community? [**Learn more about arXivLabs**](https://info.arxiv.org/labs/index.html).", "url": "https://wpnews.pro/news/agentic-detection-of-online-conspiracies", "canonical_source": "http://arxiv.org/abs/2609.30250v1", "published_at": "2026-09-25 16:46:12+00:00", "updated_at": "2026-09-25 17:00:13.624579+00:00", "lang": "en", "topics": ["artificial-intelligence", "ai-agents", "ai-research", "natural-language-processing", "ai-safety"], "entities": ["arXiv", "Hebrew Twitter", "COVID-19"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/agentic-detection-of-online-conspiracies", "markdown": "https://wpnews.pro/news/agentic-detection-of-online-conspiracies.md", "text": "https://wpnews.pro/news/agentic-detection-of-online-conspiracies.txt", "jsonld": "https://wpnews.pro/news/agentic-detection-of-online-conspiracies.jsonld"}}