Making FETCH! Happen: Finding Emergent Dog Whistles Through Common Habitats

TL;DR

This paper introduces FETCH!, a new task for detecting emerging dog whistles in social media, and EarShot, a baseline system that leverages vector databases and LLMs, highlighting current system limitations.

Contribution

The paper proposes FETCH! for identifying novel dog whistles and presents EarShot, a baseline system combining vector databases and LLMs, addressing the shortcomings of existing methods.

Findings

State-of-the-art systems underperform on social media datasets.

EarShot effectively identifies new dog whistles.

Current lexicon-based approaches struggle to keep up.

Abstract

WARNING: This paper contains content that maybe upsetting or offensive to some readers. Dog whistles are coded expressions with dual meanings: one intended for the general public (outgroup) and another that conveys a specific message to an intended audience (ingroup). Often, these expressions are used to convey controversial political opinions while maintaining plausible deniability and slip by content moderation filters. Identification of dog whistles relies on curated lexicons, which have trouble keeping up to date. We introduce FETCH!, a task for finding novel dog whistles in massive social media corpora. We find that state-of-the-art systems fail to achieve meaningful results across three distinct social media case studies. We present EarShot, a strong baseline system that combines the strengths of vector databases and Large Language Models (LLMs) to efficiently and effectively identify new dog whistles.