Mathematical modeling of sentiment analysis using TextBlob and Naïve Bayes for evaluating public discourse trends

Closed

Devi Eka Wardani Meganingtyas, Aufa Fahmi Widyatna, Allan Dinen Irlando, Gede Pramudya Ananta, Qorry Meidianingsih

2025 AIP Conference Proceedings Vol. 3372 Issue 1 Conference paper Cited by 0 SDG 17SDG 11SDG 16 Quartile

Abstract

In Indonesia, 2024 is the year of general elections for its citizens, one of which is the election of regional heads, namely candidates for governor and deputy governor of DKI Jakarta Province. There are three pairs of candidates who will participate in this election. This research was conducted to get public interest in these candidate pairs in order to provide an overview of how public trust in these candidates. The data used in this research were taken from the first debate video took place on October 6th, 2024 with 2.225 comments written by netizens on four YouTube channels, namely Kompas TV, TV One, Metro TV, and Narasi Newsroom. The methods used in this research are TextBlob and Naïve Bayes Algorithm. The sentiment ratio of 1st pair of candidate is 4,67, the 2nd pair of candidate is 4,24, and the 3rd pair of candidate is 4,45. These ratios highlight that all three candidate pairs enjoy predominantly positive sentiment, with slight variations in the strength of positivity, which may reflect differences in public perception, messaging effectiveness, or specific factors influencing public opinion. Overall, all candidates have a model accuracy above 70%, which shows that the model is quite reliable. © 2025 Author(s).

Affiliations

Department of Mathematics, Universitas Negeri Jakarta, Jakarta, Indonesia; Jabatan Ikhtisas Pendidikan Dan Siswazah, Universiti Tun Hussein Onn Malaysia, Johor Darul Ta'zim, Malaysia; Department of Mathematics Education, Universitas Negeri Jakarta, Jakarta, Indonesia

Research at a Glance

Premium content — register to unlock

Research at a Glance

Register to unlock

Topics & SDG Alignment

Premium content — register to unlock

Topics & SDG Alignment

Register to unlock

Collaboration

Premium content — register to unlock

Collaboration

Register to unlock

Author Profile (Selected)

Premium content — register to unlock

Author Profile (Selected)

Register to unlock

References Overview

Premium content — register to unlock

References Overview

Register to unlock

Journal & Source

Premium content — register to unlock

Journal & Source

Register to unlock

Metadata & Integrity

Premium content — register to unlock

Metadata & Integrity

Register to unlock