POLAR: A Per-User Association Test in Embedding Space
Abstract
Most intrinsic association probes operate at the word, sentence, or corpus level, obscuring author-level variation. We present COMPASS (COsine-Based Measure of Per-User Association with Semantic Subspaces), 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 tokens; COMPASS projects these vectors onto curated lexical axes and reports standardized effects with permutation p-values and Benjamini--Hochberg control. On a balanced bot--human Twitter benchmark, COMPASS 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.
Fields of Study & Subjects
Authorship Attribution and Profiling
Mental Health via Writing
Computational and Text Analysis Methods
Publication details
- Journal / source
- Proceedings of the International AAAI Conference on Web and Social Media
- Publisher
- Association for the Advancement of Artificial Intelligence (AAAI)
- Volume
- 20
- Issue
- 1
- Pages
- 250–261
- Publication date
- 25 May 2026
- Language
- EN