Sentiment Analysis of YouTube Comments on Indonesian 2024 Presidential Candidate Talk Show Using 1D-CNN, LSTM, and BiLSTM Models.

Saved in:

Bibliographic Details
Title:	Sentiment Analysis of YouTube Comments on Indonesian 2024 Presidential Candidate Talk Show Using 1D-CNN, LSTM, and BiLSTM Models.
Authors:	Amaliaputri, Hasna Azzahra¹ hasnazhrr@gmail.com, Wijaya, Andreas Parama² a.p.wijaya@unpar.ac.id, Salim, Daniel² daniel.salim@unpar.ac.id
Source:	IAENG International Journal of Applied Mathematics. Jul2026, Vol. 56 Issue 7, p2697-2703. 7p.
Subjects:	Sentiment analysis, Deep learning, YouTube (Web resource), Elections, Political communication, Long short-term memory
Abstract:	The rapid growth of social media has significantly transformed political communication, with YouTube emerging as a key platform for public engagement. User-generated comments, in particular, offer valuable insights into public sentiment toward political candidates. This study analyzes sentiment in YouTube comments related to the 2024 Indonesian presidential election, with a focus on videos featuring Anies Baswedan, Prabowo Subianto, and Ganjar Pranowo. Two word embedding methods -- Keras Embedding and FastText -- are evaluated in combination with three deep learning architectures: one-dimensional convolutional neural networks (1D-CNN), long short-term memory (LSTM), and bidirectional LSTM (BiLSTM). Model performance is assessed using accuracy and F1-score. The experimental results demonstrate that the BiLSTM model, combined with Keras Embedding, achieves the most consistent and competitive performance across all datasets. This model is subsequently applied to a dataset of comments collected from videos published in early 2024. The findings indicate that videos featuring Prabowo Subianto receive the highest proportion of positive sentiment, followed by those featuring Anies Baswedan, while videos featuring Ganjar Pranowo receive the lowest positive sentiment. These results highlight the effectiveness of deep learning-based sentiment analysis in gauging public opinion in an electoral context. [ABSTRACT FROM AUTHOR]
	Copyright of IAENG International Journal of Applied Mathematics is the property of International Association of Engineers (IAENG) and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)
Database:	Engineering Source

Description
Abstract:	The rapid growth of social media has significantly transformed political communication, with YouTube emerging as a key platform for public engagement. User-generated comments, in particular, offer valuable insights into public sentiment toward political candidates. This study analyzes sentiment in YouTube comments related to the 2024 Indonesian presidential election, with a focus on videos featuring Anies Baswedan, Prabowo Subianto, and Ganjar Pranowo. Two word embedding methods -- Keras Embedding and FastText -- are evaluated in combination with three deep learning architectures: one-dimensional convolutional neural networks (1D-CNN), long short-term memory (LSTM), and bidirectional LSTM (BiLSTM). Model performance is assessed using accuracy and F1-score. The experimental results demonstrate that the BiLSTM model, combined with Keras Embedding, achieves the most consistent and competitive performance across all datasets. This model is subsequently applied to a dataset of comments collected from videos published in early 2024. The findings indicate that videos featuring Prabowo Subianto receive the highest proportion of positive sentiment, followed by those featuring Anies Baswedan, while videos featuring Ganjar Pranowo receive the lowest positive sentiment. These results highlight the effectiveness of deep learning-based sentiment analysis in gauging public opinion in an electoral context. [ABSTRACT FROM AUTHOR]
ISSN:	19929978