POLAR:A Per-User Association Test in Embedding Space

TL;DR

POLAR introduces a novel per-user lexical association test operating in embedding space, enabling detailed author-level analysis and discrimination of bot and human accounts on social media.

Contribution

It presents a new method for author-level lexical association testing using embedding projections, allowing for detailed social media account analysis.

Findings

Successfully separates bots from humans on Twitter

Quantifies lexical alignment with slur lexicons on extremist forums

Reveals ideological drift over time in social media accounts

Abstract

Most intrinsic association probes operate at the word, sentence, or corpus level, obscuring author-level variation. We present POLAR (Per-user On-axis Lexical Association Re-port), a per-user lexical association test that runs in the embedding space of a lightly adapted masked language model. Authors are represented by private deterministic to-kens; POLAR projects these vectors onto curated lexicalaxes and reports standardized effects with permutation p-values and Benjamini--Hochberg control. On a balanced bot--human Twitter benchmark, POLAR cleanly separates LLM-driven bots from organic accounts; on an extremist forum,it quantifies strong alignment with slur lexicons and reveals rightward drift over time. The method is modular to new attribute sets and provides concise, per-author diagnostics for computational social science. All code is publicly avail-able at https://github.com/pedroaugtb/POLAR-A-Per-User-Association-Test-in-Embedding-Space.