Conspiracy Frame: a Semiotically-Driven Approach for Conspiracy Theories Detection

TL;DR

This paper introduces Conspiracy Frame, a semiotic-based semantic representation and dataset for detecting conspiracy theories in Telegram messages, exploring how frame-based approaches can improve understanding and recognition of conspiratorial narratives.

Contribution

It presents a novel semiotic-driven semantic framework and dataset for conspiracy theory detection, and investigates the role of frames in enhancing recognition by large language models.

Findings

Frames show potential in conspiracy detection tasks.

Annotated spans reveal semantic patterns like 'Kinship' and 'Ingest_substance'.

In-context frame injection does not significantly boost performance.

Abstract

Conspiracy theories are anti-authoritarian narratives that lead to social conflict, impacting how people perceive political information. To help in understanding this issue, we introduce the Conspiracy Frame: a fine-grained semantic representation of conspiratorial narratives derived from frame-semantics and semiotics, which spawned the Conspiracy Frames (Con.Fra.) dataset: a corpus of Telegram messages annotated at span-level. The Conspiracy Frame and Con.Fra. dataset contribute to the implementation of a more generalizable understanding and recognition of conspiracy theories. We observe the ability of LLMs to recognize this phenomenon in-domain and out-of-domain, investigating the role that frames may have in supporting this task. Results show that, while the injection of frames in an in-context approach does not lead to clear increase of performance, it has potential; the mapping of annotated spans with FrameNet shows abstract semantic patterns (e.g., `Kinship', `Ingest\_substance') that potentially pave the way for a more semantically- and semiotically-aware detection of conspiratorial narratives.