Agentic Detection of Online Conspiracies

2026-09-24

AI Summary

This study addresses the challenge of distinguishing implicit intents, such as sarcasm and criticism, in conspiracy theory detection on social media. To this end, it proposes an agent-based framework equipped with social query tools that reformulates detection as a socially grounded interpretation task. Through an adaptive reasoning mechanism, the framework invokes external tools on demand to retrieve socio-contextual evidence, thereby accurately inferring speakers’ true intents. Experiments conducted on a large-scale Hebrew tweet dataset demonstrate that the proposed framework significantly outperforms conventional text classification and non-agent baselines under adversarial testing conditions. These results validate the effectiveness of the context-aware workflow. Furthermore, this work provides a systematic analysis of the trade-off between reasoning performance and computational efficiency.

Abstract

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. We 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. These 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.

Problem

• conspiracy detection
• illocutionary force
• intent inference
• social media discourse
• context-aware classification

Innovation

• Agentic Framework
• Conspiracy Detection
• Illocutionary Force
• Social Context
• Adaptive Reasoning