Analisis Sentimen Debat Capres 2024 pada Media Sosial Youtube Menggunakan Algoritma Recurrent Neural Network (RNN)
DOI:
https://doi.org/10.62951/repeater.v4i4.1029Keywords:
2024 Presidential Debate, Long Short-Term Memory (LSTM), Multiclass Classification, Recurrent Neural Network, Sentiment AnalysisAbstract
The 2024 Presidential Debate was a pivotal moment in Indonesia's democratic process, significantly influencing public perception and political decisions, particularly among swing voters and undecided voters. The comment section on YouTube serves as a representative platform capturing public emotional responses, opinions, and arguments regarding the performance of candidate pairs. This study aims to evaluate the effectiveness and measure the accuracy of the Recurrent Neural Network (RNN) algorithm with Long Short-Term Memory (LSTM) architecture in classifying multiclass sentiments (7 classes) related to the First 2024 Presidential Debate. Data was collected via web crawling using the YouTube Data API v3 from the metrotvnews and KPU RI channels, yielding a total of 23,163 comments. Following deduplication and text preprocessing stages (case folding, filtering, slang normalization, tokenizing, stopword removal, and Sastrawi stemming), 6,000 comments were manually annotated for model training. Experimental evaluations demonstrate that the LSTM model achieved an accuracy of 91.08%, an F1-score of 93.40%, a recall of 91.44%, and a precision of 95.61%. Sentiment distribution analysis reveals that Candidate Pair 01 (Anies Baswedan) dominated the positive sentiment with 35.0% (2,281 comments), followed by negative sentiment toward Candidate Pair 02 (Prabowo Subianto) at 15.4% (1,003 comments). These findings prove that the LSTM algorithm is highly reliable in modeling sequential dependencies in Indonesian political text.
Downloads
References
Chollet, F. (2018). Deep learning with Python. Manning Publications.
CNBC Indonesia. (2023, December). 6 survei terbaru pasca 2 debat: Prabowo vs Anies vs Ganjar.
Dharmawan, S., Mawardi, V. C., & Perdana, N. J. (2023). Klasifikasi ujaran kebencian menggunakan metode FeedForward Neural Network (IndoBERT). Jurnal Ilmu Komputer dan Sistem Informasi, 11(1). https://doi.org/10.24912/jiksi.v11i1.24066
Dwitama, A. P. J. (2021). Deteksi ujaran kebencian pada Twitter bahasa Indonesia menggunakan machine learning: Reviu literatur. Jurnal Komputer dan Informatika, 1. https://doi.org/10.20885/snati.v1i1.5
Dwitama, A. P. J., Fudholi, D. H., & Hidayat, S. (2023). Indonesian hate speech detection using bidirectional Long Short-Term Memory (Bi-LSTM). Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi), 7(2), 302–309. https://doi.org/10.29207/resti.v7i2.4642
Ibrohim, M. O., Setiadi, M. A., & Budi, I. (2019). Identification of hate speech and abusive language on Indonesian Twitter using the Word2vec, part of speech and emoji features. In Proceedings of the 1st International Conference on Advanced Information Science and System (pp. 1–5). Association for Computing Machinery. https://doi.org/10.1145/3373477.3373495
Kemp, S. (2023a). Digital 2023: Indonesia. DataReportal.
Kemp, S. (2023b). The changing world of digital in 2023. We Are Social & Meltwater.
Komisi Pemilihan Umum Republik Indonesia. (2023). KPU siap gelar debat capres 3 kali dan cawapres 2 kali. https://www.kpu.go.id/berita/baca/12125/kpu-siap-gelar-debat-capres-3-kali-dan-cawapres-2-kali
Lestandy, M., Abdurrahim, A., & Syafa’ah, L. (2021). Analisis sentimen tweet vaksin COVID-19 menggunakan Recurrent Neural Network dan Naïve Bayes. Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi), 5(4), 802–808. https://doi.org/10.29207/resti.v5i4.3308
Manullang, M. T. R., et al. (2021). Deteksi hoaks pada berita lokal Indonesia menggunakan model berbasis Recurrent Neural Network. RINarxiv.
Marpaung, A., Rismala, R., & Nurrahmi, H. (2021). Hate speech detection in Indonesian Twitter texts using bidirectional gated recurrent unit. In 2021 13th International Conference on Knowledge and Smart Technology (KST) (pp. 186–190). https://doi.org/10.1109/KST51265.2021.9415760
Ramadhan, & Krisiandi. (2023, December). Survei Litbang Kompas Pilpres 2024: Undecided voters capai 28,7 persen. Kompas.com.
Sazany, E., & Budi, I. (2019). Hate speech identification in text written in Indonesian with Recurrent Neural Network. In 2019 International Conference on Advanced Computer Science and Information Systems (ICACSIS) (pp. 211–216). https://doi.org/10.1109/ICACSIS47736.2019.8979959
Tang, D., & Zhang, M. (2017). Deep learning in natural language processing. Springer.
Taradhita, D. A. N., & Putra, I. K. G. D. (2021). Hate speech classification in Indonesian language tweets by using Convolutional Neural Network. Journal of ICT Research and Applications, 14(3), 225–239. https://doi.org/10.5614/itbj.ict.res.appl.2021.14.3.2
Wahyuni, W. (2024, January). Manfaat debat capres dan cawapres bagi calon pemilih. Hukumonline.com.
Fahmi. (2023, December). Analisis cepat debat capres #1 [Post]. X.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Repeater : Publikasi Teknik Informatika dan Jaringan

This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.




