Ensemble Hybrid LSTM, SVM, dan Lexicon-Based untuk Analisis Sentimen Ulasan TikTok Bahasa Indonesia Informal
-
Roki Akbar
*
universitas bina sarana informatika, Pontianak,
Indonesia
- Windi Irmayani universitas bina sarana informatika, Pontianak, Indonesia
- Muhammad Ifan Rifani Ihsan universitas bina sarana informatika, Pontianak, Indonesia (*) Corresponding Author
Abstract
Penelitian ini mengembangkan pendekatan Ensemble Hybrid untuk analisis sentimen ulasan aplikasi TikTok berbahasa Indonesia informal dengan mengintegrasikan tiga metode: Long Short-Term Memory (LSTM), Support Vector Machine (SVM), dan Lexicon-Based Methods. Masalah utama penelitian adalah tingginya volume ulasan pengguna dan kompleksitas bahasa informal yang menyulitkan analisis manual. Dataset yang digunakan terdiri dari 29.385 ulasan pengguna TikTok dari Google Play Store. Proses preprocessing meliputi enam tahapan: case folding, cleansing, tokenisasi, normalisasi slang, stopword removal, dan stemming. Evaluasi kinerja dilakukan menggunakan metrik accuracy, precision, recall, dan F1-Score. Hasil pengujian menunjukkan bahwa metode tunggal terbaik adalah SVM dengan akurasi 90,61%, diikuti LSTM (87,08%) dan Lexicon-Based (85,96%). Pendekatan Ensemble Hybrid yang mengintegrasikan ketiga metode berhasil meningkatkan akurasi menjadi 92,15%. Peningkatan ini membuktikan bahwa integrasi metode efektif menangani variasi linguistik informal.
References
We Are Social & Meltwater, “Digital 2025: Indonesia,” We Are Social, 2025. [Online]. Available: https://wearesocial.com/id/blog/2025/01/digital-2025-indonesia/
D. Wahyuni, N. Fadhillah, W. Ariestya, and U. Gunadarma, “Analisis Sentimen Ulasan Aplikasi TikTok Menggunakan Pendekatan Berbasis Fitur,” J. Ilm. Teknol. Inf., vol. 23, no. 2, pp. 173–180, 2024.
A. F. T. Winata et al., “Challenges in Indonesian Natural Language Processing: Informal Text and Code-Mixing,” Proc. Int. Conf. Adv. Comput. Sci. Inf. Syst., 2021, pp. 123–128.
A. Sulthan et al., “Perbandingan Kinerja SVM dan LSTM dalam Analisis Sentimen Ulasan Pengguna,” Prosiding Semin. Nas. Informat., 2024, pp. 45–52.
S. Ratnaswari, N. C. Wibowo, D. Satria, and Y. Kartika, “Analisis Sentimen Menggunakan Metode Lexicon-Based dan Support Vector Machine pada Ulasan Presiden dan Wakil Presiden Indonesia,” J. Teknol. Inf. dan Komputer, vol. 13, no. 1, pp. 362–368, 2025.
F. D. Sari and W. Widayat, “Analisis Sentimen Masyarakat Terhadap PON 2024 di Twitter Menggunakan Algoritma SVM dan KNN,” J. Sist. Inf., vol. 22, no. 2, pp. 251–265, 2025.
E. D. Shanty, B. A. Jayadi, and V. C. Mawardi, “Penerapan Metode SVM dengan Pendekatan InSet Lexicon-Based pada Layanan E-Ticketing Kereta Api,” J. Teknol. Inf. Terap., vol. 9, no. 1, pp. 99–108, 2025.
L. Rokach, “Ensemble-Based Classifiers,” Artif. Intell. Rev., vol. 33, no. 1–2, pp. 1–39, 2010.
S. Hochreiter and J. Schmidhuber, “Long Short-Term Memory,” Neural Comput., vol. 9, no. 8, pp. 1735–1780, 1997.
C. Cortes and V. Vapnik, “Support-Vector Networks,” Mach. Learn., vol. 20, no. 3, pp. 273–297, 1995.
M. Taboada, J. Brooke, M. Tofiloski, K. Voll, and M. Stede, “Lexicon-Based Methods for Sentiment Analysis,” Comput. Linguist., vol. 37, no. 2, pp. 267–307, 2011.
A. F. T. Winata et al., “IndoBERT: An Indonesian Pre-trained Language Model,” arXiv preprint arXiv:2109.02076, 2021.
N. V. Chawla, K. W. Bowyer, L. O. Hall, and W. P. Kegelmeyer, “SMOTE: Synthetic Minority Over-sampling Technique,” J. Artif. Intell. Res., vol. 16, pp. 321–357, 2002.
T. Mikolov, I. Sutskever, K. Chen, G. S. Corrado, and J. Dean, “Distributed Representations of Words and Phrases and their Compositionality,” Adv. Neural Inf. Process. Syst., vol. 26, pp. 3111–3119, 2013.
D. P. Kingma and J. Ba, “Adam: A Method for Stochastic Optimization,” Proc. Int. Conf. Learn. Represent., 2015.
E. Cambria, “Affective Computing and Sentiment Analysis,” IEEE Intell. Syst., vol. 31, no. 2, pp. 102–107, 2016.
M. E. M. A. Rahman and M. A. H. Akhand, “Sentiment Analysis of Social Media Text Using Hybrid Approach,” J. Big Data, vol. 8, no. 1, p. 112, 2021.
S. R. G. and P. K. S., “Hybrid Ensemble Learning for Sentiment Analysis: A Review,” IEEE Access, vol. 10, pp. 112345–112360, 2022.
Kaggle, “TikTok App Reviews Dataset,” Kaggle.com, 2024. [Online]. Available: https://www.kaggle.com/datasets
Universitas Bina Sarana Informatika, “Pedoman Penulisan Skripsi Program Studi Informatika,” Pontianak, Indonesia, 2024.
Bila bermanfaat silahkan share artikel ini
Berikan Komentar Anda terhadap artikel Ensemble Hybrid LSTM, SVM, dan Lexicon-Based untuk Analisis Sentimen Ulasan TikTok Bahasa Indonesia Informal
Pages: 134-141
Copyright (c) 2026 Roki Akbar, Windi Irmayani, Muhammad Ifan Rifani Ihsan
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under Creative Commons Attribution 4.0 International License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (Refer to The Effect of Open Access).
