open access

Journal of Artificial Intelligence and Digital Health

P e e r - R e v i e w e d  
Bi-Annual (Two issues per year)

ISSN: 3139-6267 (Online)
DOI Prefix (Crossref): 10.67238

Transformer-based Framework for Election Outcome Prediction using Electorate Opinion
Research Article - Volume: 1, Issue: 2, 2026 (September)
Transformer-based Framework for Election Outcome Prediction using Electorate Opinion Download PDF

Umoh Augustine Uduak1,5*, Victor Eshiet Ekong2,5, Temitope Joel Fakiesi3,5, Philip Asuquo4,5

1Department of Information Systems, Faculty of Computing, University of Uyo, Uyo, Nigeria
2Department of Software Engineering, Faculty of Computing, University of Uyo, Uyo, Nigeria
3Department of Computer Science, Faculty of Computing, University of Uyo, Uyo, Nigeria
4Department of computer Engineering, Faculty of Engineering, University of Uyo, Uyo, Nigeria
5Tetfund Center of Excellence in Computational Intelligence, University of Uyo, Uyo, Nigeria

*Correspondence to: Umoh Augustine Uduak 1,5, 1Department of Information Systems, Faculty of Computing, University of Uyo, Uyo, Nigeria; 5Tetfund Center of Excellence in Computational Intelligence, University of Uyo, Uyo, Nigeria, E-mail:

Received: July 20, 2026; Manuscript No: JAID-26-2523; Editor Assigned: July 27, 2026; PreQc No: JAID-26-2523 (PQ); Reviewed: August 06, 2026; Revised: August 17, 2026; Manuscript No: JAID-26-2523 (R); Published: September 09, 2026

ABSTRACT

The accurate prediction of election outcomes plays a pivotal role in enhancing democratic processes by offering insights into voter behaviour and informing strategic decision-making for policymakers, political parties, and media organizations. This study introduces a novel framework leveraging the Robustly Optimized BERT Pretraining Approach (RoBERTa) to predict election results through sentiment analysis of public opinions expressed on X (formerly Twitter). By analyzing nuanced linguistic patterns in social media discourse, the research addresses the challenges of sentiment ambiguity and class imbalance. A case study on the 2023 Nigerian presidential election, focusing on Akwa Ibom State, demonstrates the effectiveness of this framework. The RoBERTa model achieved notable accuracy in predicting election outcomes, highlighting its potential for bridging the gap between online sentiment and real-world electoral results. The model achieved a higher precision, recall, and F1-score for the Negative class, with values of 0.95, 0.97, and 0.96, respectively, indicating exceptional performance in identifying and classifying negative sentiments. This framework underscores the transformative power of transformer-based architectures in electoral studies, offering avenues for more transparent and data-driven decision-making in political analysis.

Keywords: Election; Transformer; Prediction; RoBERTa; Sentiment

Citation: Uduak UA, Ekong VE, Fakiesi TJ, Asuquo P (2026). Transformer-based Framework for Election Outcome Prediction using Electorate Opinion. J. Artif. Intell. Digit. Health. Vol.1 Iss.2, September (2026), pp:160-169.
Copyright: © 2026 Umoh Augustine Uduak, Victor Eshiet Ekong, Temitope Joel Fakiesi, Philip Asuquo. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.