POLAR:A Per-User Association Test in Embedding Space

2026-03-16

AI Summary

针对作者层面词汇关联难以量化的问题，提出POLAR方法，在嵌入空间中通过投影至词汇轴并结合置换检验，实现个体用户的关联分析。

Technology Category

• Natural Language Processing: Discourse, Pragmatics & Argument Mining
• Reasoning under Uncertainty: Relational Probabilistic Models
• Machine Learning: Learning Preferences or Rankings

Application Category

• User Modeling, Personalization and Recommendation: User privacy protection in personalized systems
• Web Mining and Content Analysis: Content-based information diffusion
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs

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.

Problem

• lexical association
• author-level variation
• embedding space
• computational social science
• per-user analysis

Innovation

• per-user embedding
• lexical association test
• semantic axes
• permutation testing
• computational social science