MODEL TERBARUKAN HYBIRD CNN DAN LEXICON-BASED UNTUK MENDETEKSI SENTIMEN PUBLIK TERHADAP DANANTARA
Kata Kunci:
convolutional neural network (CNN), danantara, lexicon-based, natural language processing (NLP), sentiment analysis
Abstrak
Danantara merupakan dana kekayaan negara yang mendapat perhatian luas di media sosial, termasuk di “X”. Berbagai opini publik tentang danantara muncul, baik dalam sentimen positif maupun negatif. Untuk memahami persepsi masyarakat secara lebih akurat, diperlukan metode analisis sentimen yang efektif. Metode Lexicon-Based sering digunakan tetapi memiliki keterbatasan dalam menangkap konteks, sementara Convolutional Neural Network (CNN) mampu mengenali pola dalam teks tetapi membutuhkan banyak data. Maka dari itu penelitian ini bertujuan untuk mengembangkan model hybird CNN dan Lexicon-based guna meningkatkan akurasi analisis sentimen publik terhadap Danantara. Data akan dikumpulkan dari media sosial “X” menggunakan metode scraping atau API, kemudian melalui proses preprocessing sebelum dianalisis menggunakan pendekatan hybird. Evaluasi model dilakukan dengan membandingkan performa CNN, Lexicon-based dan hybird model menggunakan metrik seperti akurasi, precision, recall dan F1-Score. Hasil peneltian ini memberikan model yang lebih akurat dalam memahmi opini publik serta memberikan wawasan bagi pemangku kebijakan dalam merancang strategi komunikasi yang lebih efektif dengan tingkat akurasi sebesar 86%. Selain itu peneliti juga akan berkontribusi dalam pengembangan Natural Languange Processing (NLP) dana analisis sentimen berbasis deep learning.
Referensi
[1] L. Ellyanti, Y. Ruldeviyani, L. E. Pradana, and A. Harjanto, “Sentiment Analysis of Twitter Users to the PeduliLindungi Using Naïve Bayes Algorithm,” Jurnal RESTI, vol. 7, no. 2, pp. 414–421, Apr. 2023, doi: 10.29207/resti.v7i2.4684.
[2] L. Kothamasu and E. Kannan, “Sentiment analysis on twitter data based on spider monkey optimiza-tion and deep learning for future prediction of the brands,” Concurr Comput, vol. 34, Jun. 2022, doi: 10.1002/cpe.7104.
[3] Stefanno Sulaiman and Ananda Teresia, “New In-donesia sovereign wealth fund to invest $20 billion in projects,” https://www.reuters.com/world/asia-pacific/indonesias-prabowo-officially-establishes-new-sovereign-wealth-fund-2025-02-24/, Jakarta, Feb. 24, 2025.
[4] K. Kevin, M. Enjeli, and A. Wijaya, “Analisis Sen-timen Pengunaaan Aplikasi Kinemaster Menggunakan Metode Naive Bayes,” Jurnal Ilmiah Computer Science, vol. 2, no. 2, pp. 89–98, Jan. 2024, doi: 10.58602/jics.v2i2.24.
[5] A. Larasati, Y. R. W. N. Susanto, E. Mohamad, and A. R. Purnama, “A Sentiment Analysis Using Fuzzy Support Vector Machine Algorithm,” Buletin Ilmiah Sarjana Teknik Elektro, vol. 5, no. 4, pp. 467–474, Dec. 2023, doi: 10.12928/biste.v5i4.9363.
[6] A. Larasati, Y. R. W. N. Susanto, E. Mohamad, and A. R. Purnama, “A Sentiment Analysis Using Fuzzy Support Vector Machine Algorithm,” Buletin Ilmiah Sarjana Teknik Elektro, vol. 5, no. 4, pp. 467–474, Dec. 2023, doi: 10.12928/biste.v5i4.9363.
[7] A. Larasati, Y. R. W. N. Susanto, E. Mohamad, and A. R. Purnama, “A Sentiment Analysis Using Fuzzy Support Vector Machine Algorithm,” Buletin Ilmiah Sarjana Teknik Elektro, vol. 5, no. 4, pp. 467–474, Nov. 2023, doi: 10.12928/biste.v5i4.9363.
[8] L. Yang, Y. Li, J. Wang, and R. S. Sherratt, “Senti-ment Analysis for E-Commerce Product Reviews in Chinese Based on Sentiment Lexicon and Deep Learning,” IEEE Access, vol. 8, pp. 23522–23530, 2020, doi: 10.1109/ACCESS.2020.2969854.
[9] A. Chugh et al., “Spider Monkey Crow Optimization Algorithm with Deep Learning for Sentiment Classi-fication and Information Retrieval,” IEEE Access, vol. 9, pp. 24249–24262, 2021, doi: 10.1109/ACCESS.2021.3055507.
[10] F. Fitroh and F. Hudaya, “Systematic Literature Re-view: Analisis Sentimen Berbasis Deep Learning,” Jurnal Nasional Teknologi dan Sistem Informasi, vol. 9, no. 2, pp. 132–140, Aug. 2023, doi: 10.25077/teknosi.v9i2.2023.132-140.
[11] M. Kamyab, G. Liu, and M. Adjeisah, “Attention-Based CNN and Bi-LSTM Model Based on TF-IDF and GloVe Word Embedding for Sentiment Analy-sis,” Applied Sciences (Switzerland), vol. 11, no. 23, Dec. 2021, doi: 10.3390/app112311255.
[12] D. Y. Liliana, N. N. Hikmah, and M. Harjono, “Pengembangan Sistem Pemantauan Sentimen Beri-ta Berbahasa Indonesia Berdasarkan Konten Dengan Long Short-Term Memory The Develop-ment Of Content-Based Indonesian News Sentiment Monitoring System Using Long Short-Term Memory,” Jurnal Teknologi Informasi dan Ilmu Komputer (JTIIK), vol. 8, no. 5, pp. 995–1002, Oct. 2021, doi: 10.25126/jtiik.202184624.
[13] M. V. Shyahrin, Y. Sibaroni, and D. Puspandari, “Penerapan Metode Long Short-Term Memory dan Word2Vec dalam Analisis Sentimen Ulasan pada Aplikasi Ferizy,” Techno.COM, vol. 22, no. 4, pp. 833–842, Nov. 2023.
[14] T. Abdillah, U. Khaira, and B. F. Hutabarat, “Komparasi Metode Naive Bayes dan K-Nearest Neighbors Terhadap Analisis Sentimen Pengguna Aplikasi Zenius,” Jurnal PROCESSOR, vol. 19, no. 1, May 2024, doi: 10.33998/processor.2024.19.1.1596.
[15] Riskawati, Fatihanursari, Iin, and A. R. Rinaldi, “Penerapan Metode Naïve Bayes Classifier Pada Analisis Sentimen Aplikasi Gopay,” Jurnal Maha-siswa Teknik Informatika (JATI), vol. 8, no. 1, Feb. 2024.
[16] D. S. Putri and T. Ridwan, “Analisis Sentimen Ulasan Aplikasi Pospay dengan Algoritma Support Vector Machine,” Jurnal Ilmiah Informatika (JIF), vol. 11, no. 1, Mar. 2023.
[17] L. Yang, Y. Li, J. Wang, and R. S. Sherratt, “Senti-ment Analysis for E-Commerce Product Reviews in Chinese Based on Sentiment Lexicon and Deep Learning,” IEEE Access, vol. 8, Jan. 2020, doi: 10.1109/ACCESS.2020.2969854.
[18] Y. Liu, S. Wang, and S. Yu, “A Bullet Screen Senti-ment Analysis Method That Integrates the Sentiment Lexicon with RoBERTa-CNN,” Electronics (Swit-zerland), vol. 13, no. 20, Oct. 2024, doi: 10.3390/electronics13203984.
[19] Y. Liu, S. Wang, and S. Yu, “A Bullet Screen Senti-ment Analysis Method That Integrates the Sentiment Lexicon with RoBERTa-CNN,” Electronics (Swit-zerland), vol. 13, no. 20, Oct. 2024, doi: 10.3390/electronics13203984.
[20] A. Kumar and S. Shekhar, “Hybrid Framework Inte-grating Lexicon and Learning Methods for Enhanc-ing Sentiment Analysis Based on Patients’ Tweets on Medicines,” Journal Electrical Systems, vol. 20, no. 6, pp. 2786–2810, 2024.
[21] M. Aljabri et al., “Sentiment analysis of arabic tweets regarding distance learning in saudi arabia during the covid-19 pandemic,” Sensors, vol. 21, no. 16, Aug. 2021, doi: 10.3390/s21165431.
[22] Y. Fauziah, B. Yuwono, and A. S. Aribowo, “Lexi-con Based Sentiment Analysis in Indonesia Lan-guages : A Systematic Literature Review,” RSF Con-ference Series: Engineering and Technology, vol. 1, no. 1, pp. 363–367, Dec. 2021, doi: 10.31098/cset.v1i1.397.
[23] M. Birjali, M. Kasri, and A. Beni-Hssane, “A com-prehensive survey on sentiment analysis: Ap-proaches, challenges and trends,” Knowl Based Syst, vol. 226, Aug. 2021, doi: 10.1016/j.knosys.2021.107134.
[24] A. Kumar and S. Shekhar, “Hybrid Framework Inte-grating Lexicon and Learning Methods for Enhanc-ing Sentiment Analysis Based on Patients’ Tweets on Medicines,” 2024.
[25] A. P. P. Sitanggang, “Hybrid CNN And RNNS Model For Sentiment Analysis,” PROXIES, vol. 8, no. 1, 2024.
[26] S. J and K. U, “Sentiment analysis of amazon user reviews using a hybrid approach,” Measurement: Sensors, vol. 27, p. 100790, 2023, doi: https://doi.org/10.1016/j.measen.2023.100790.
[27] Y. Cheng, L. Yao, G. Xiang, G. Zhang, T. Tang, and L. Zhong, “Text Sentiment Orientation Analysis Based on Multi-Channel CNN and Bidirectional GRU with Attention Mechanism,” IEEE Access, vol. 8, pp. 134964–134975, 2020, doi: 10.1109/ACCESS.2020.3005823.
[28] T. Yuan, H. H. Li, H. Y. Zhao, Q. H. Cai, H. Liu, and X. H. Hu, “Multi-Channel Convolutional Neural Network for Targeted Sentiment Classification,” in Proceedings - International Conference on Ma-chine Learning and Cybernetics, IEEE Computer Society, Jul. 2019. doi: 10.1109/ICMLC48188.2019.8949286.
[29] L. Yang, Y. Li, J. Wang, and R. S. Sherratt, “Senti-ment Analysis for E-Commerce Product Reviews in Chinese Based on Sentiment Lexicon and Deep Learning,” IEEE Access, vol. 8, pp. 23522–23530, 2020, doi: 10.1109/ACCESS.2020.2969854.
[30] B. Shin, T. Lee, and J. D. Choi, “Lexicon Integrated CNN Models with Attention for Sentiment Analy-sis,” in Proceedings of the EMNLP Workshop on Computational Approaches to Subjectivity, Senti-ment and Social Media Analysis, Cornell Universi-ty, Oct. 2016. [Online]. Available: http://arxiv.org/abs/1610.06272
[2] L. Kothamasu and E. Kannan, “Sentiment analysis on twitter data based on spider monkey optimiza-tion and deep learning for future prediction of the brands,” Concurr Comput, vol. 34, Jun. 2022, doi: 10.1002/cpe.7104.
[3] Stefanno Sulaiman and Ananda Teresia, “New In-donesia sovereign wealth fund to invest $20 billion in projects,” https://www.reuters.com/world/asia-pacific/indonesias-prabowo-officially-establishes-new-sovereign-wealth-fund-2025-02-24/, Jakarta, Feb. 24, 2025.
[4] K. Kevin, M. Enjeli, and A. Wijaya, “Analisis Sen-timen Pengunaaan Aplikasi Kinemaster Menggunakan Metode Naive Bayes,” Jurnal Ilmiah Computer Science, vol. 2, no. 2, pp. 89–98, Jan. 2024, doi: 10.58602/jics.v2i2.24.
[5] A. Larasati, Y. R. W. N. Susanto, E. Mohamad, and A. R. Purnama, “A Sentiment Analysis Using Fuzzy Support Vector Machine Algorithm,” Buletin Ilmiah Sarjana Teknik Elektro, vol. 5, no. 4, pp. 467–474, Dec. 2023, doi: 10.12928/biste.v5i4.9363.
[6] A. Larasati, Y. R. W. N. Susanto, E. Mohamad, and A. R. Purnama, “A Sentiment Analysis Using Fuzzy Support Vector Machine Algorithm,” Buletin Ilmiah Sarjana Teknik Elektro, vol. 5, no. 4, pp. 467–474, Dec. 2023, doi: 10.12928/biste.v5i4.9363.
[7] A. Larasati, Y. R. W. N. Susanto, E. Mohamad, and A. R. Purnama, “A Sentiment Analysis Using Fuzzy Support Vector Machine Algorithm,” Buletin Ilmiah Sarjana Teknik Elektro, vol. 5, no. 4, pp. 467–474, Nov. 2023, doi: 10.12928/biste.v5i4.9363.
[8] L. Yang, Y. Li, J. Wang, and R. S. Sherratt, “Senti-ment Analysis for E-Commerce Product Reviews in Chinese Based on Sentiment Lexicon and Deep Learning,” IEEE Access, vol. 8, pp. 23522–23530, 2020, doi: 10.1109/ACCESS.2020.2969854.
[9] A. Chugh et al., “Spider Monkey Crow Optimization Algorithm with Deep Learning for Sentiment Classi-fication and Information Retrieval,” IEEE Access, vol. 9, pp. 24249–24262, 2021, doi: 10.1109/ACCESS.2021.3055507.
[10] F. Fitroh and F. Hudaya, “Systematic Literature Re-view: Analisis Sentimen Berbasis Deep Learning,” Jurnal Nasional Teknologi dan Sistem Informasi, vol. 9, no. 2, pp. 132–140, Aug. 2023, doi: 10.25077/teknosi.v9i2.2023.132-140.
[11] M. Kamyab, G. Liu, and M. Adjeisah, “Attention-Based CNN and Bi-LSTM Model Based on TF-IDF and GloVe Word Embedding for Sentiment Analy-sis,” Applied Sciences (Switzerland), vol. 11, no. 23, Dec. 2021, doi: 10.3390/app112311255.
[12] D. Y. Liliana, N. N. Hikmah, and M. Harjono, “Pengembangan Sistem Pemantauan Sentimen Beri-ta Berbahasa Indonesia Berdasarkan Konten Dengan Long Short-Term Memory The Develop-ment Of Content-Based Indonesian News Sentiment Monitoring System Using Long Short-Term Memory,” Jurnal Teknologi Informasi dan Ilmu Komputer (JTIIK), vol. 8, no. 5, pp. 995–1002, Oct. 2021, doi: 10.25126/jtiik.202184624.
[13] M. V. Shyahrin, Y. Sibaroni, and D. Puspandari, “Penerapan Metode Long Short-Term Memory dan Word2Vec dalam Analisis Sentimen Ulasan pada Aplikasi Ferizy,” Techno.COM, vol. 22, no. 4, pp. 833–842, Nov. 2023.
[14] T. Abdillah, U. Khaira, and B. F. Hutabarat, “Komparasi Metode Naive Bayes dan K-Nearest Neighbors Terhadap Analisis Sentimen Pengguna Aplikasi Zenius,” Jurnal PROCESSOR, vol. 19, no. 1, May 2024, doi: 10.33998/processor.2024.19.1.1596.
[15] Riskawati, Fatihanursari, Iin, and A. R. Rinaldi, “Penerapan Metode Naïve Bayes Classifier Pada Analisis Sentimen Aplikasi Gopay,” Jurnal Maha-siswa Teknik Informatika (JATI), vol. 8, no. 1, Feb. 2024.
[16] D. S. Putri and T. Ridwan, “Analisis Sentimen Ulasan Aplikasi Pospay dengan Algoritma Support Vector Machine,” Jurnal Ilmiah Informatika (JIF), vol. 11, no. 1, Mar. 2023.
[17] L. Yang, Y. Li, J. Wang, and R. S. Sherratt, “Senti-ment Analysis for E-Commerce Product Reviews in Chinese Based on Sentiment Lexicon and Deep Learning,” IEEE Access, vol. 8, Jan. 2020, doi: 10.1109/ACCESS.2020.2969854.
[18] Y. Liu, S. Wang, and S. Yu, “A Bullet Screen Senti-ment Analysis Method That Integrates the Sentiment Lexicon with RoBERTa-CNN,” Electronics (Swit-zerland), vol. 13, no. 20, Oct. 2024, doi: 10.3390/electronics13203984.
[19] Y. Liu, S. Wang, and S. Yu, “A Bullet Screen Senti-ment Analysis Method That Integrates the Sentiment Lexicon with RoBERTa-CNN,” Electronics (Swit-zerland), vol. 13, no. 20, Oct. 2024, doi: 10.3390/electronics13203984.
[20] A. Kumar and S. Shekhar, “Hybrid Framework Inte-grating Lexicon and Learning Methods for Enhanc-ing Sentiment Analysis Based on Patients’ Tweets on Medicines,” Journal Electrical Systems, vol. 20, no. 6, pp. 2786–2810, 2024.
[21] M. Aljabri et al., “Sentiment analysis of arabic tweets regarding distance learning in saudi arabia during the covid-19 pandemic,” Sensors, vol. 21, no. 16, Aug. 2021, doi: 10.3390/s21165431.
[22] Y. Fauziah, B. Yuwono, and A. S. Aribowo, “Lexi-con Based Sentiment Analysis in Indonesia Lan-guages : A Systematic Literature Review,” RSF Con-ference Series: Engineering and Technology, vol. 1, no. 1, pp. 363–367, Dec. 2021, doi: 10.31098/cset.v1i1.397.
[23] M. Birjali, M. Kasri, and A. Beni-Hssane, “A com-prehensive survey on sentiment analysis: Ap-proaches, challenges and trends,” Knowl Based Syst, vol. 226, Aug. 2021, doi: 10.1016/j.knosys.2021.107134.
[24] A. Kumar and S. Shekhar, “Hybrid Framework Inte-grating Lexicon and Learning Methods for Enhanc-ing Sentiment Analysis Based on Patients’ Tweets on Medicines,” 2024.
[25] A. P. P. Sitanggang, “Hybrid CNN And RNNS Model For Sentiment Analysis,” PROXIES, vol. 8, no. 1, 2024.
[26] S. J and K. U, “Sentiment analysis of amazon user reviews using a hybrid approach,” Measurement: Sensors, vol. 27, p. 100790, 2023, doi: https://doi.org/10.1016/j.measen.2023.100790.
[27] Y. Cheng, L. Yao, G. Xiang, G. Zhang, T. Tang, and L. Zhong, “Text Sentiment Orientation Analysis Based on Multi-Channel CNN and Bidirectional GRU with Attention Mechanism,” IEEE Access, vol. 8, pp. 134964–134975, 2020, doi: 10.1109/ACCESS.2020.3005823.
[28] T. Yuan, H. H. Li, H. Y. Zhao, Q. H. Cai, H. Liu, and X. H. Hu, “Multi-Channel Convolutional Neural Network for Targeted Sentiment Classification,” in Proceedings - International Conference on Ma-chine Learning and Cybernetics, IEEE Computer Society, Jul. 2019. doi: 10.1109/ICMLC48188.2019.8949286.
[29] L. Yang, Y. Li, J. Wang, and R. S. Sherratt, “Senti-ment Analysis for E-Commerce Product Reviews in Chinese Based on Sentiment Lexicon and Deep Learning,” IEEE Access, vol. 8, pp. 23522–23530, 2020, doi: 10.1109/ACCESS.2020.2969854.
[30] B. Shin, T. Lee, and J. D. Choi, “Lexicon Integrated CNN Models with Attention for Sentiment Analy-sis,” in Proceedings of the EMNLP Workshop on Computational Approaches to Subjectivity, Senti-ment and Social Media Analysis, Cornell Universi-ty, Oct. 2016. [Online]. Available: http://arxiv.org/abs/1610.06272
Diterbitkan
2026-06-13
##submission.howToCite##
Wijaya, A., & Thomas Filikano. (2026). MODEL TERBARUKAN HYBIRD CNN DAN LEXICON-BASED UNTUK MENDETEKSI SENTIMEN PUBLIK TERHADAP DANANTARA. TEKNIMEDIA: Teknologi Informasi Dan Multimedia, 7(1), 22-30. https://doi.org/10.46764/teknimedia.v7i1.357
Terbitan
Bagian
Articles
##submission.copyrightStatement##
##submission.license.cc.by-sa4.footer##Semua tulisan pada jurnal ini menjadi tanggungjawab penuh penulis. Jurnal Teknimedia memberikan akses terbuka terhadap siapapun agar informasi dan temuan pada artikel tersebut bermanfaat bagi semua orang. Jurnal Teknimedia dapat diakses dan diunduh secara gratis, tanpa dipungut biaya, sesuai dengan lisensi creative commons yang digunakan.
Jurnal TEKNIMEDIA : Teknologi Informasi dan Multimedia is licensed under a Lisensi Creative Commons Atribusi-BerbagiSerupa 4.0 Internasional
.png)
