PRISM: A Framework for Producing Interpretable Political Bias Embeddings with Political-Aware Cross-Encoder

TL;DR

PRISM is a novel framework that generates interpretable political bias embeddings by extracting bias indicators from news data and aligning embeddings with these indicators, improving bias classification and interpretability.

Contribution

It introduces a two-stage process combining bias indicator mining and cross-encoder embeddings to produce interpretable political bias representations.

Findings

Outperforms state-of-the-art models in political bias classification

Provides highly interpretable bias embeddings

Enhances ideological analysis and diversified retrieval

Abstract

Semantic Text Embedding is a fundamental NLP task that encodes textual content into vector representations, where proximity in the embedding space reflects semantic similarity. While existing embedding models excel at capturing general meaning, they often overlook ideological nuances, limiting their effectiveness in tasks that require an understanding of political bias. To address this gap, we introduce PRISM, the first framework designed to Produce inteRpretable polItical biaS eMbeddings. PRISM operates in two key stages: (1) Controversial Topic Bias Indicator Mining, which systematically extracts fine-grained political topics and their corresponding bias indicators from weakly labeled news data, and (2) Cross-Encoder Political Bias Embedding, which assigns structured bias scores to news articles based on their alignment with these indicators. This approach ensures that embeddings are explicitly tied to bias-revealing dimensions, enhancing both interpretability and predictive power. Through extensive experiments on two large-scale datasets, we demonstrate that PRISM outperforms state-of-the-art text embedding models in political bias classification while offering highly interpretable representations that facilitate diversified retrieval and ideological analysis. The source code is available at https://github.com/dukesun99/ACL-PRISM.