Answers are grounded in this paper and cite their sources.
As online social networks (OSNs) play an increasingly influential role in political communication, accurately detecting political stance from noisy, short-form content remains a significant challenge in computational social science (CSS). This paper presents a controlled comparison of text classification models for political stance detection during the 2024 U.S. presidential election, focusing on candidate affiliation toward Donald Trump and Joe Biden–Kamala Harris. Using nearly 100,000 posts from X, we define candidate affiliation as a three-class target variable (Trump, Biden–Kamala, or Neutral) and use topic modeling to support keyword development and thematic characterization. Under a unified preprocessing, labeling, and evaluation pipeline, we compare classical machine learning models, sentence-embedding-based neural architectures, and a domain-adapted transformer. Results suggest that task-aligned text representation accounts for most of the predictive signal in this setting. While fine-tuned BERTweet achieves the strongest in-domain performance, carefully engineered classical models, particularly linear support vector machines, remain highly competitive. Multi-feature and ablation analyses further indicate that expanded metadata did not yield reliable gains beyond strong text representations. Overall, this work provides a controlled comparison of text models for candidate affiliation on a heuristically labeled corpus.
No takes yet. Share an insight, caveat, or question.
Wang et al. (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: