Melola Discovery

← Melola Discovery

Jurnal

Modified Convolutional Neural Network for Sentiment Classification: A Case Study on The Indonesian Electoral Commission

Scientific Journal of Informatics · Vol. 11 No. 2 (2024) · hlm. 493–506

DOI
10.15294/sji.v11i2.4929
ISSN
2407-7658, 2460-0040
Terbit
2024-06-12
Penerbit
Universitas Negeri Semarang
Bahasa
eng

Abstrak

Purpose: This study aims to analyze public sentiment towards the Indonesian Electoral Commission (KPU) performance and evaluate a modified Convolutional Neural Network (CNN) model effectiveness in sentiment analysis. Methods: This research employs several methods to achieve its objectives. First, data collection was conducted using web crawling techniques to gather public opinions on the performance of the Indonesian Electoral Commission for the 2024 elections, with a specific focus on platform X. A total of 5,782 data points were collected and underwent preprocessing before sentiment analysis was performed. This study uses the CNN method due to its exceptional ability to recognize patterns and features in text data through its convolutional layers. CNN is highly effective in sentiment analysis tasks because of its ability to capture local context and spatial features from text data, which is crucial for understanding the nuances of sentiment in comments. The modified CNN model was then trained and evaluated using a labeled dataset, where each comment was classified into positive, negative, or neutral sentiment categories. Modifying the CNN model involved adjusting its architecture and parameters, as well as adding layers such as batch normalization and dropout to optimize its performance. The effectiveness of the modified CNN model was assessed based on metrics such as classification accuracy, precision, recall, and F1 score. Through this methodological approach, the research aims to gain insights into public sentiment towards the KPU performance in the 2024 elections and to evaluate the effectiveness of the modified CNN model in sentiment analysis. Result: The research revealed several significant findings. Firstly, most comments expressed concerns regarding performance aspects of KPU’s, including transparency, fairness, and integrity. Neutral sentiment dominated the discourse, with approximately 23.66% of comments conveying dissatisfaction or skepticism towards KPU's handling of the elections. Additionally, sentiments expressed on social media platform X mirrored those found across other platforms, indicating a consistent perception of KPU performance among users. Furthermore, the evaluation of the modified CNN model demonstrated a substantial improvement in accuracy, achieving an impressive 93% accuracy rate compared to the pre-modification model's accuracy of 77%. These results suggest that the modifications made to the CNN model effectively enhanced its performance in sentiment analysis tasks related to KPU performance during the 2024 elections. These findings contribute to a deeper understanding of public sentiment toward KPU performance and underscore the importance of leveraging advanced technology, such as modified CNN models, for sentiment analysis. Novelty: This study contributes novelty in several ways. Firstly, it provides insights into public sentiment towards the performance of the KPU during the 2024 General Elections, which is crucial for understanding the perception of democracy in Indonesia. Second, the study employs a mixed-methods approach, combining web crawling techniques for data collection and a modified CNN model for sentiment analysis, which offers a comprehensive and advanced methodology for analyzing sentiments on social media platforms. Thirdly, the evaluation of the modified CNN model demonstrates a significant improvement in accuracy, indicating the approach's efficacy in analyzing sentiments related to KPU performance. This study offers valuable contributions to academic research and practical applications in sentiment analysis, particularly in democratic processes and institutional performance evaluation.

Kata kunci

Jaringan kolaborasi para penulis

19 penulis · 62 tautan kepenulisan bersama · 22 lintas organisasi

Arahkan kursor atau ketuk sebuah nama untuk menyorot rekan penulisnya. Klik dua kali untuk membuka halaman penulis.

  • Muhammadiyah University of Yogyakarta
  • National Defence University of Malaysia
  • Mercu Buana University
  • Mahidol University
  • University of Malaya
  • Universiti Malaysia Pahang Al-Sultan Abdullah
  • Organisasi berbeda
  • Organisasi sama
  • Afiliasi tidak diketahui
  • Garis lebih tebal = lebih banyak artikel bersama · lingkaran lebih besar = lebih banyak artikel
Tampilkan sebagai tabel
Rekan penulisOrganisasiArtikel bersama
Laila Ma’rifatul AzizahMuhammadiyah University of Yogyakarta2
Fauri HakimMuhammadiyah University of Yogyakarta2
Sartika PuspitaMuhammadiyah University of Yogyakarta2
Erma SofianiMuhammadiyah University of Yogyakarta2
Desta AtikanandaMuhammadiyah University of Yogyakarta2
Annisa Divayu AndriyaniUniversiti Malaysia Pahang Al-Sultan Abdullah2
Ida NurhaidaMercu Buana University1
Chong Mei ChanUniversity of Malaya1
Farindira Vesti RahmasariMuhammadiyah University of Yogyakarta1
Wulan NovianiMuhammadiyah University of Yogyakarta1
Titih HuriahMuhammadiyah University of Yogyakarta1
Ferika IndarwatiMuhammadiyah University of Yogyakarta1
Umniyyah AgsanieMuhammadiyah University of Yogyakarta1
Tesaviani KusumastiwiMuhammadiyah University of Yogyakarta1
Mallika ImwongMahidol University1

Afiliasi berasal dari OpenAlex; metadata OAI-PMH jurnal tidak memuatnya. Penulis tanpa ID OpenAlex dicocokkan berdasarkan nama, sehingga dua orang bisa tergabung atau satu orang bisa terpisah.

Sumber metadata: OAI-PMH (metadata jurnal) https://journal.unnes.ac.id/journals/sji/oai, pertama di-harvest 6 Nov 2026, terakhir terlihat 8 Nov 2026.
Metadata asli (oai_dc)
<oai_dc:dc xmlns="http://www.openarchives.org/OAI/2.0/" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:oai_dc="http://www.openarchives.org/OAI/2.0/oai_dc/" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.openarchives.org/OAI/2.0/oai_dc/  http://www.openarchives.org/OAI/2.0/oai_dc.xsd">
	<dc:title xml:lang="en">Modified Convolutional Neural Network for Sentiment Classification: A Case Study on The Indonesian Electoral Commission</dc:title>
	<dc:creator xml:lang="en">Riyadi, Slamet</dc:creator>
	<dc:creator xml:lang="en">Mahardika, Naufal Gita </dc:creator>
	<dc:creator xml:lang="en">Damarjati, Cahya</dc:creator>
	<dc:creator xml:lang="en">Ramli, Suzaimah</dc:creator>
	<dc:subject xml:lang="en">Sentiment analysis</dc:subject>
	<dc:subject xml:lang="en">KPU</dc:subject>
	<dc:subject xml:lang="en">CNN</dc:subject>
	<dc:subject xml:lang="en">Deep learning</dc:subject>
	<dc:subject xml:lang="en">General election</dc:subject>
	<dc:description xml:lang="en">Purpose: This study aims to analyze public sentiment towards the Indonesian Electoral Commission (KPU) performance and evaluate a modified Convolutional Neural Network (CNN) model effectiveness in sentiment analysis.
Methods: This research employs several methods to achieve its objectives. First, data collection was conducted using web crawling techniques to gather public opinions on the performance of the Indonesian Electoral Commission for the 2024 elections, with a specific focus on platform X. A total of 5,782 data points were collected and underwent preprocessing before sentiment analysis was performed. This study uses the CNN method due to its exceptional ability to recognize patterns and features in text data through its convolutional layers. CNN is highly effective in sentiment analysis tasks because of its ability to capture local context and spatial features from text data, which is crucial for understanding the nuances of sentiment in comments. The modified CNN model was then trained and evaluated using a labeled dataset, where each comment was classified into positive, negative, or neutral sentiment categories. Modifying the CNN model involved adjusting its architecture and parameters, as well as adding layers such as batch normalization and dropout to optimize its performance. The effectiveness of the modified CNN model was assessed based on metrics such as classification accuracy, precision, recall, and F1 score. Through this methodological approach, the research aims to gain insights into public sentiment towards the KPU performance in the 2024 elections and to evaluate the effectiveness of the modified CNN model in sentiment analysis.
Result: The research revealed several significant findings. Firstly, most comments expressed concerns regarding performance aspects of KPU’s, including transparency, fairness, and integrity. Neutral sentiment dominated the discourse, with approximately 23.66% of comments conveying dissatisfaction or skepticism towards KPU's handling of the elections. Additionally, sentiments expressed on social media platform X mirrored those found across other platforms, indicating a consistent perception of KPU performance among users. Furthermore, the evaluation of the modified CNN model demonstrated a substantial improvement in accuracy, achieving an impressive 93% accuracy rate compared to the pre-modification model's accuracy of 77%. These results suggest that the modifications made to the CNN model effectively enhanced its performance in sentiment analysis tasks related to KPU performance during the 2024 elections. These findings contribute to a deeper understanding of public sentiment toward KPU performance and underscore the importance of leveraging advanced technology, such as modified CNN models, for sentiment analysis.
Novelty: This study contributes novelty in several ways. Firstly, it provides insights into public sentiment towards the performance of the KPU during the 2024 General Elections, which is crucial for understanding the perception of democracy in Indonesia. Second, the study employs a mixed-methods approach, combining web crawling techniques for data collection and a modified CNN model for sentiment analysis, which offers a comprehensive and advanced methodology for analyzing sentiments on social media platforms. Thirdly, the evaluation of the modified CNN model demonstrates a significant improvement in accuracy, indicating the approach's efficacy in analyzing sentiments related to KPU performance. This study offers valuable contributions to academic research and practical applications in sentiment analysis, particularly in democratic processes and institutional performance evaluation.</dc:description>
	<dc:publisher xml:lang="en">Universitas Negeri Semarang</dc:publisher>
	<dc:date>2024-06-12</dc:date>
	<dc:type>info:eu-repo/semantics/article</dc:type>
	<dc:type>info:eu-repo/semantics/publishedVersion</dc:type>
	<dc:type xml:lang="en">Peer-reviewed Article</dc:type>
	<dc:format>application/pdf</dc:format>
	<dc:identifier>https://journal.unnes.ac.id/journals/sji/article/view/4929</dc:identifier>
	<dc:identifier>10.15294/sji.v11i2.4929</dc:identifier>
	<dc:source xml:lang="en">Scientific Journal of Informatics; Vol. 11 No. 2: Regular Issue; 493-506</dc:source>
	<dc:source>2407-7658</dc:source>
	<dc:source>2460-0040</dc:source>
	<dc:language>eng</dc:language>
	<dc:relation>https://journal.unnes.ac.id/journals/sji/article/view/4929/530</dc:relation>
	<dc:rights xml:lang="en">Copyright (c) 2024 Scientific Journal of Informatics</dc:rights>
</oai_dc:dc>