Overview

The transmission of conspiracy theories poses a significant concern given their potential to undermine public trust and increase societal divisions. These narratives, often sensationalist and unsupported by credible evidence, can transmit misinformation, and influence public opinion on critical issues.

Timely detection of conspiracy theories is paramount for governments and policymakers. Quick identification allows for proactive measures to prevent the spread of such theories, preserving public trust and providing accurate information to constituents.

Currently, most conspiracy detection models demand extensive manual labelling of data for each unique conspiracy theory. This process often spans several months, resulting in a model whose scope is limited to the conspiracies present in its training data. In an age where new conspiracy narratives can surface overnight, policymakers and governments cannot afford such delays.

To address this challenge, this project proposes an innovative approach to conspiracy theory detection by applying social science theory to identify thematic and narrative structures associated with conspiratorial thinking. These insights can then be embedded into the training data for state-of-the-art large language models tasked with classifying conspiracy theories within text data.

Building models which consider these conspiratorial markers in the classification process could improve detection models’ ability to identify new conspiracy theories with minimal data. The ability to train models with minimal data would allow for faster paced classification of emerging conspiracy theories. A faster detection tool for emerging conspiracy theories will aid in the ability of governments and policymakers to combat such theories before they cause societal harms.