Digital Democracy: Analyzing Political Sentiments through Multinomial Naive Bayes in Election Campaign Ads
Abstract
This research delves into sentiment analysis for digital election campaign advertisements using the Multinomial Naive Bayes approach. The study addresses the limitations of standard sentiment analysis methodologies in capturing the intricacies of public sentiments toward political ads. The dataset, sourced from Kaggle, encompasses 3000 records with sentiments categorized as positive, neutral, and negative. The Multinomial Naive Bayes model demonstrated a substantial accuracy increase from 92% to 96%, outperforming the standard Naive Bayes model. Precision, recall, and F1-score metrics consistently improved across sentiment categories. While dataset representativeness and cultural specificity pose limitations, the research contributes significantly to sentiment analysis methodologies in politically charged digital environments. Future research recommendations include exploring advanced NLP techniques, incorporating real-time data from diverse social media platforms, and addressing ethical considerations in political sentiment analysis. The outcomes emphasize the importance of tailored methodologies for enhanced accuracy in understanding sentiments expressed in digital election campaign advertisements.
Downloads
References
J. Chester and K. C. Montgomery, “The Digital Commercialisation of US Politics — 2020 and Beyond,” Internet Policy Review, 2019, doi: 10.14763/2019.4.1443.
E. F. Fowler, M. M. Franz, and T. N. Ridout, “Online Political Advertising in the United States,” in Social Media and Democracy, N. Persily and J. A. Tucker, Eds., in SSRC Anxieties of Democracy. , Cambridge: Cambridge University Press, 2020, pp. 111–138. [Online]. Available: https://www.cambridge.org/core/product/98F09A1F61A67819A70C22920BE4674D
M. Hoferer, L. Böttcher, H. J. Herrmann, and H. Gersbach, “The Impact of Technologies in Political Campaigns,” Physica a Statistical Mechanics and Its Applications, 2020, doi: 10.1016/j.physa.2019.122795.
L. Terán and J. Mancera, “Dynamic Profiles Using Sentiment Analysis for VAA’s Recommendation Design,” Procedia Computer Science, 2017, doi: 10.1016/j.procs.2017.05.265.
Y. M. Kim, “Algorithmic Opportunity: Digital Advertising and Inequality in Political Involvement,” The Forum, 2016, doi: 10.1515/for-2016-0034.
J. N. Sheth, “How Social Media Will Impact Marketing Media,” 2018, doi: 10.1007/978-981-10-5323-8_1.
A. Ballard, D. S. Hillygus, and T. Konitzer, “Campaigning Online: Web Display Ads in the 2012 Presidential Campaign,” Ps Political Science & Politics, 2016, doi: 10.1017/s1049096516000780.
M. A. Xenos, T. Macafee, and A. Pole, “Understanding Variations in User Response to Social Media Campaigns: A Study of Facebook Posts in the 2010 US Elections,” New Media & Society, 2015, doi: 10.1177/1461444815616617.
M. Aggarwal et al., “A 2 Million-Person, Campaign-Wide Field Experiment Shows How Digital Advertising Affects Voter Turnout,” Nature Human Behaviour, 2023, doi: 10.1038/s41562-022-01487-4.
G. Alvarez, “Good News, Bad News: A Sentiment Analysis of the 2016 Election Russian Facebook Ads,” 2020.
R. Sandoval‐Almazán and D. Valle-Cruz, “Sentiment Analysis of Facebook Users Reacting to Political Campaign Posts,” Digital Government Research and Practice, 2020, doi: 10.1145/3382735.
A. Sheingate, J. Scharf, and C. Delahanty, “Digital Advertising in U.S. Federal Elections, 2004-2020,” Journal of Quantitative Description Digital Media, 2022, doi: 10.51685/jqd.2022.026.
M. Qorib, R. Gizaw, and J. Kim, “Impact of Sentiment Analysis for the 2020 U.S. Presidential Election on Social Media Data,” 2023, doi: 10.1145/3589883.3589888.
O. Olabanjo, A. S. Wusu, R. Padonu, O. Afisi, and M. Mazzara, “Twitter Sentiment Analysis of Lagos State 2023 Gubernatorial Election Using BERT,” Journal of Advanced Research in Social Sciences, 2023, doi: 10.33422/jarss.v6i2.1027.
P. Koromilas, M. A. Nicolaou, Θ. Γιαννακόπουλος, and Y. Panagakis, “MMATR: A Lightweight Approach for Multimodal Sentiment Analysis Based on Tensor Methods,” 2023, doi: 10.1109/icassp49357.2023.10097030.
M. Huisheng, B. Zhang, H. Xu, Z. Yuan, and Y. Liu, “Robust-Msa: Understanding the Impact of Modality Noise on Multimodal Sentiment Analysis,” Proceedings of the Aaai Conference on Artificial Intelligence, 2023, doi: 10.1609/aaai.v37i13.27078.
M. Jeyakarthic and A. Leoraj, “A Novel Social Media-Based Adaptable Approach for Sentiment Analysis Data,” 2023, doi: 10.1109/iceeict56924.2023.10156976.
H. Prasetyo and A. S. Fitrani, “Sentiment Analysis Before Presidential Election 2024 Using Naïve Bayes Classifier Based on Public Opinion in Twitter,” Procedia of Engineering and Life Science, 2023, doi: 10.21070/pels.v4i0.1395.
V. Nurcahyawati and Z. Mustaffa, “Improving Sentiment Reviews Classification Performance Using Support Vector Machine-Fuzzy Matching Algorithm,” Bulletin of Electrical Engineering and Informatics, 2023, doi: 10.11591/eei.v12i3.4830.
D. S. Zingade, R. K. Deshmukh, and D. B. Kadam, “Sentiment Analysis Using Multi-Objective Optimization-Based Feature Selection Approach,” 2023, doi: 10.1109/incet57972.2023.10169912.
D. Utari, “Sentiment Analysis of the COVID-19 Booster Vaccine With the Naïve Bayes Algorithm,” Procedia of Engineering and Life Science, 2023, doi: 10.21070/pels.v4i0.1379.
R. B. Dahlian and D. Sitanggang, “Sentiment Analysis of Digital Television Migration on Twitter Using Naïve Bayes Multinomial Comparison, Support Vector Machines, and Logistic Regression Algorithms,” Jurnal Sisfokom (Sistem Informasi Dan Komputer), 2023, doi: 10.32736/sisfokom.v12i2.1668.
P. Gaur, S. Vashistha, and P. J. Jha, “Twitter Sentiment Analysis Using Naive Bayes-Based Machine Learning Technique,” 2023, doi: 10.1007/978-981-19-5443-6_27.
Y. Astuti, S. N. Wahyuni, D. Maulina, and F. M. Sidiq, “The Data Leakage Sentiment Analysis Using Naive Bayes Algorithm Based on Machine Learning Approach,” 2022, doi: 10.1109/isriti56927.2022.10052877.
W. B. Zulfikar, A. R. Atmadja, and S. F. Pratama, “Sentiment Analysis on Social Media Against Public Policy Using Multinomial Naive Bayes,” Scientific Journal of Informatics, 2023, doi: 10.15294/sji.v10i1.39952.
K. Chan and S. Im, “Sentiment Analysis by Using Naïve‐Bayes Classifier With Stacked CARU,” Electronics Letters, 2022, doi: 10.1049/ell2.12478.
A. Rachmad, Y. Kustiyahningsih, R. I. Pratama, M. A. Syakur, E. M. S. Rochman, and D. P. Hapsari, “Sentiment Analysis of Government Policy Management on the Handling of Covid-19 Using Naive Bayes With Feature Selection,” 2022, doi: 10.1109/itis57155.2022.10010004.
