Science Publications

Sign Up
Sign In
Submit
Current Research in Public Health
Cite This Article Share Download PDF XML
  1. Home
  2. Journals
  3. Current Research in Public Health
  4. Archive
  5. Volume 6, Issue 1, 2026
  6. Article
Article Open Access February 06, 2026

Predictive Modeling of Public Sentiment Using Social Media Data and Natural Language Processing Techniques

Lawrence A. Farinola 1, 2 and Jean-Eudes Assogba 1, 2
1
Department of Software Engineering, Faculty of Architecture and Engineering, Rauf Denktas University, Mersin 10 via Turkey
2
Center of Excellence for Interdisciplinary AI and Data Science Research, Rauf Denktas University, Mersin 10 via Turkey
Publihed in: Current Research in Public Health (Volume 6, Issue 1, 2026)
Page(s): 1-12
DOI: 10.31586/jaibd.2026.6162
Received
July 24, 2025
Revised
October 30, 2025
Accepted
February 02, 2026
Published
February 06, 2026
Keywords
Sentiment Analysis; Social Media Mining; Public Opinion Prediction; Natural Language Processing; BERT Transformer Model
Creative Commons

This is an Open Access article, distributed under the terms of the Creative Commons Attribution 4.0 International License (http://creativecommons.org/licenses/by/4.0/), which permits unrestricted use, distribution and reproduction in any medium or format, provided the original work is properly cited.
Copyright: Copyright © The Author(s), 2026. Published by Scientific Publications
Article metrics
Views
1
Downloads
0

Cite This Article

APA Style
Farinola, L. A. , & Assogba, J. (2026). Predictive Modeling of Public Sentiment Using Social Media Data and Natural Language Processing Techniques. Current Research in Public Health, 6(1), 1-12. https://doi.org/10.31586/jaibd.2026.6162
ACS Style
Farinola, L. A. ; Assogba, J. Predictive Modeling of Public Sentiment Using Social Media Data and Natural Language Processing Techniques. Current Research in Public Health 2026 6(1), 1-12. https://doi.org/10.31586/jaibd.2026.6162
Chicago/Turabian Style
Farinola, Lawrence A., and Jean-Eudes Assogba. 2026. "Predictive Modeling of Public Sentiment Using Social Media Data and Natural Language Processing Techniques". Current Research in Public Health 6, no. 1: 1-12. https://doi.org/10.31586/jaibd.2026.6162
AMA Style
Farinola LA, Assogba J. Predictive Modeling of Public Sentiment Using Social Media Data and Natural Language Processing Techniques. Current Research in Public Health. 2026; 6(1):1-12. https://doi.org/10.31586/jaibd.2026.6162 
@Article{crph6162,
AUTHOR = {Farinola, Lawrence A. and Assogba, Jean-Eudes},
TITLE = {Predictive Modeling of Public Sentiment Using Social Media Data and Natural Language Processing Techniques},
JOURNAL = {Current Research in Public Health},
VOLUME = {6},
YEAR = {2026},
NUMBER = {1},
PAGES = {1-12},
URL = {https://www.scipublications.com/journal/index.php/JAIBD/article/view/6162},
ISSN = {2831-5162},
DOI = {10.31586/jaibd.2026.6162},
ABSTRACT = {Social media platforms like X (formerly Twitter) generate vast volumes of user-generated content that provide real-time insights into public sentiment. Despite the widespread use of traditional machine learning methods, their limitations in capturing contextual nuances in noisy social media text remain a challenge. This study leverages the Sentiment140 dataset, comprising 1.6 million labeled tweets, and develops predictive models for binary sentiment classification using Naive Bayes, Logistic Regression, and the transformer-based BERT model. Experiments were conducted on a balanced subset of 12,000 tweets after comprehensive NLP preprocessing. Evaluation using accuracy, F1-score, and confusion matrices revealed that BERT significantly outperforms traditional models, achieving an accuracy of 89.5% and an F1-score of 0.89 by effectively modeling contextual and semantic nuances. In contrast, Naive Bayes and Logistic Regression demonstrated reasonable but consistently lower performance. To support practical deployment, we introduce SentiFeel, an interactive tool enabling real-time sentiment analysis. While resource constraints limited the dataset size and training epochs, future work will explore full corpus utilization and the inclusion of neutral sentiment classes. These findings underscore the potential of transformer models for enhanced public opinion monitoring, marketing analytics, and policy forecasting.},
}
%0 Journal Article
%A Farinola, Lawrence A.
%A Assogba, Jean-Eudes
%D 2026
%J Current Research in Public Health

%@ 2831-5162
%V 6
%N 1
%P 1-12

%T Predictive Modeling of Public Sentiment Using Social Media Data and Natural Language Processing Techniques
%M doi:10.31586/jaibd.2026.6162
%U https://www.scipublications.com/journal/index.php/JAIBD/article/view/6162

TY  - JOUR
AU  - Farinola, Lawrence A.
AU  - Assogba, Jean-Eudes
TI  - Predictive Modeling of Public Sentiment Using Social Media Data and Natural Language Processing Techniques
T2  - Current Research in Public Health
PY  - 2026
VL  - 6
IS  - 1
SN  - 2831-5162
SP  - 1
EP  - 12
UR  - https://www.scipublications.com/journal/index.php/JAIBD/article/view/6162
AB  - Social media platforms like X (formerly Twitter) generate vast volumes of user-generated content that provide real-time insights into public sentiment. Despite the widespread use of traditional machine learning methods, their limitations in capturing contextual nuances in noisy social media text remain a challenge. This study leverages the Sentiment140 dataset, comprising 1.6 million labeled tweets, and develops predictive models for binary sentiment classification using Naive Bayes, Logistic Regression, and the transformer-based BERT model. Experiments were conducted on a balanced subset of 12,000 tweets after comprehensive NLP preprocessing. Evaluation using accuracy, F1-score, and confusion matrices revealed that BERT significantly outperforms traditional models, achieving an accuracy of 89.5% and an F1-score of 0.89 by effectively modeling contextual and semantic nuances. In contrast, Naive Bayes and Logistic Regression demonstrated reasonable but consistently lower performance. To support practical deployment, we introduce SentiFeel, an interactive tool enabling real-time sentiment analysis. While resource constraints limited the dataset size and training epochs, future work will explore full corpus utilization and the inclusion of neutral sentiment classes. These findings underscore the potential of transformer models for enhanced public opinion monitoring, marketing analytics, and policy forecasting.
DO  - Predictive Modeling of Public Sentiment Using Social Media Data and Natural Language Processing Techniques
TI  - 10.31586/jaibd.2026.6162
ER  -