Political stance detection on X during the 2024 U.S. election: a comparative study of classical, neural, and transformer models
Social Network Analysis and Mining · 14.11.2026
DOI: 10.1007/s13278-026-01656-7 ↗Kurz gefasst
Fachartikel in der Zeitschrift Social Network Analysis and Mining, online erschienen am 14.11.2026. Verfasst von Qile Wang und 5 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
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.
Zitieren
APA
Wang, Q., Ostadrahimi, S., Faghri, S., Baksh, M., Mauriello, M. L., & Barner, K. E. (2026). Political stance detection on X during the 2024 U.S. election: a comparative study of classical, neural, and transformer models. Social Network Analysis and Mining. https://doi.org/10.1007/s13278-026-01656-7
Vancouver
Wang Q, Ostadrahimi S, Faghri S, Baksh M, Mauriello ML, Barner KE. Political stance detection on X during the 2024 U.S. election: a comparative study of classical, neural, and transformer models. Social Network Analysis and Mining. 2026. doi:10.1007/s13278-026-01656-7
BibTeX
@article{Wang2026,
author = {Wang, Qile and Ostadrahimi, Sahar and Faghri, Safoura and Baksh, Mohammad and Mauriello, Matthew Louis and Barner, Kenneth E.},
title = {Political stance detection on X during the 2024 U.S. election: a comparative study of classical, neural, and transformer models},
journal = {Social Network Analysis and Mining},
year = {2026},
doi = {10.1007/s13278-026-01656-7}
}
EUVIMED