Adaptive Ensembling: Unsupervised Domain Adaptation for Political Document Analysis

TL;DR

This paper introduces adaptive ensembling, an unsupervised domain adaptation framework with a novel text classification model and time-aware training, improving political document analysis across different corpora and time periods.

Contribution

It presents a new unsupervised domain adaptation method with a time-aware training approach tailored for political document analysis.

Findings

Outperforms strong benchmarks in experiments.

More stable and better representation learning.

Extracts cleaner corpora for detailed analysis.

Abstract

Insightful findings in political science often require researchers to analyze documents of a certain subject or type, yet these documents are usually contained in large corpora that do not distinguish between pertinent and non-pertinent documents. In contrast, we can find corpora that label relevant documents but have limitations (e.g., from a single source or era), preventing their use for political science research. To bridge this gap, we present \textit{adaptive ensembling}, an unsupervised domain adaptation framework, equipped with a novel text classification model and time-aware training to ensure our methods work well with diachronic corpora. Experiments on an expert-annotated dataset show that our framework outperforms strong benchmarks. Further analysis indicates that our methods are more stable, learn better representations, and extract cleaner corpora for fine-grained analysis.