Analisis Perbandingan Pelabelan Inset Lexicon dan MBERT pada Sentimen Danantara Menggunakan SVM dengan Kernel Trick
DOI:
https://doi.org/10.30865/jurikom.v13i2.9629Keywords:
Inset Lexicon, MBERT, Support Vector Machine, Danantara, Sentiment AnalysisAbstract
This study aims to compare the Inset Lexicon and MBERT sentiment labeling methods for analyzing sentiment related to the Danantara issue using a Support Vector Machine (SVM) with Linear, RBF, Polynomial, and Sigmoid kernels. The main issues in this study are the suboptimal sentiment labeling methods for Indonesian-language data that can accurately capture linguistic context, as well as the uncertainty regarding the best labeling method when combined with various TF-IDF-based SVM kernels. Model evaluation uses metrics such as Accuracy, Precision, Recall, F1-score, and Cross-validation (CV). The results show that the Inset Lexicon labeling method with a Linear kernel yields the highest Accuracy of 81% with a CV of 78%, Precision of 87%, and Recall of 92%. The RBF kernel achieved an Accuracy of 78% with a CV of 76%, followed by the Sigmoid kernel at 79% Accuracy with a CV of 76%, and the Polynomial kernel at 65% Accuracy with a CV of 65%. The highest F1-score for the negative class using the Linear kernel reached 89%. Meanwhile, in MBERT labeling, the highest accuracy was achieved by the RBF kernel at 72% with a CV of 71%, followed by the Linear kernel with an accuracy of 71%, then the Polynomial kernel with an accuracy of 68%, and the Sigmoid kernel with an accuracy of 67%. The highest F1-score was found in the negative class at 79% using the RBF kernel. Overall, the negative class showed the most consistent performance, while the neutral class had the lowest Recall and F1-score values for almost all kernel types. These findings confirm that an in-depth comparative analysis between lexicon-based and deep learning-based approaches demonstrates that methods such as the Inset Lexicon can deliver better and more stable performance on Indonesian-language data.
References
[1] P. Ni, E. V. Daniel, M. H. Athallah, S. Rainhard, and L. Gaol, “PENGAWASAN DAN PERTANGGUNGJAWABAN BADAN PENGELOLA INVESTASI DANANTARA DALAM PENGELOLAAN RISIKO KERUGIAN INVESTASI KEUANGAN NEGARA,” J. Huk. Statut., vol. 4 Nomor 2, pp. 129–143, 2025.
[2] D. M. Kgs M Aria Hidayatullah, Dhamayanti, “Analisis Sentimen Pelanggan Pempek Cek Ida Terhadap Penilaian Produk Menggunakan Layanan GoFood Pada Aplikasi Gojek Dengan Klasifikasi Support Vector Machine ( SVM ),” J. Ilm. Inform. Glob., vol. 16, no. 2, pp. 264–273, 2025.
[3] A. Widodo, B. A. Herlambang, and R. Renaldy, “Optimizing Support Vector Machine ( SVM ) for Sentiment Analysis of Blu by BCA Reviews with Chi-Square,” J. Appl. informatics Comput., vol. 9, no. 5, pp. 2588–2597, 2025.
[4] P. Sunarko, A. Bijaksana, P. Negara, and R. Septiriana, “Perbandingan Klasifikasi Algoritma Support vector machine dan Naïve Bayes Menggunakan Labeling VADER dan Lexicon based pada Tweets Bahasa Indonesia dan Bahasa Inggris,” J. Apl. dan Ris. Inform., vol. 03, no. 1, pp. 9–19, 2024, doi: 10.26418/juara.v3i1.86468.
[5] H. Firda et al., “Perbandingan Pelabelan Rating - based dan Inset Lexicon - based Perbandingan Pelabelan Rating - based dan Inset Lexicon - based dalam Analisis Sentimen Menggunakan SVM ( Studi Kasus : Ulasan Aplikasi GoBiz di Google Play Store ),” J. Sist. Inf., vol. 14, pp. 516–528, 2025.
[6] N. E. Oktaviana et al., “ANALISIS SENTIMEN TERHADAP KEBIJAKAN KULIAH DARING SELAMA PANDEMI MENGGUNAKAN PENDEKATAN LEXICON BASED FEATURES DAN SUPPORT VECTOR MACHINE,” J. Teknol. Inf. dan ilmu Komput., vol. 9, no. 2, 2022, doi: 10.25126/jtiik.202295625.
[7] F. M. Apriansyah, T. I. Ramadhan, C. R. Hidayat, and A. Karta, “Perbandingan IndoBERT dan IndoRoBERTa Untuk Analisis Sentimen Pada Film Dokumenter Dirty Vote,” J. Pengemb. IT, vol. 10, no. 3, pp. 593–605, 2025, doi: 10.30591/jpit.v10i3.8607.
[8] K. Dedes et al., “BERT Sentimen : Fine-Tuning Multibahasa untuk Ulasan Bahasa,” J. Komput. Teknol. Inf. Sist. Komput., vol. 4, no. 2, pp. 1080–1084, 2025.
[9] Y. Asri, W. N. Suliyanti, D. Kuswardani, and M. Fajri, “Pelabelan Otomatis Lexicon Vader dan Klasifikasi Naive Bayes dalam menganalisis sentimen data ulasan PLN Mobile,” J. Pengkaj. dan Penerapan Tek. Inform., vol. 15, no. 2, pp. 264–275, 2022.
[10] F. F. R. Agnia Suci Rizkia, Wufron, “Analisis Sentimen Coretax : Perbandingan Pelabelan Data Manual, Transformers-Based, dan Lexicon-Based pada Performa IndoBERT,” Indones. J. Mach. Learn. Comput. Sci., vol. 5, no. July, pp. 1037–1048, 2025.
[11] C. J. L. Tobing, I. G. N. L. Wijayakusuma, and Luh Putu Ida, “Perbandingan Kinerja IndoBERT dan MBERT untuk Deteksi Berita Hoaks Politik dalam Bahasa Indonesia,” J. Sains dan Teknol., vol. 14, no. 1, pp. 114–123, 2025.
[12] A. Ulinuha, E. Majid, and R. Nuari, “PERBANDINGAN KINERJA METRIK BERT DAN MODEL MACHINE LEARNING KLASIK ( SVM , NAIVE BAYES ) UNTUK ANALISIS SENTIMEN,” J. Inovtek Polbeng, vol. 10, no. 2, pp. 741–752, 2025.
[13] P. Fremmuzar and A. Baita, “Uji Kernel SVM dalam Analisis Sentimen Terhadap Layanan Telkomsel di Media Sosial Twitter,” J. Sist. Komput., vol. 12, no. 148, 2023, doi: 10.34010/komputika.v12i2.9460.
[14] A. N. Indraini and I. Ernawati, “Analisis Sentimen Terhadap Pembelajaran Daring Di Indonesia Menggunakan Support Vector Machine ( SVM ),” J. Ilm. FIFO, vol. XIV, no. 1, pp. 68–80, 2022.
[15] L. Rohmatun and A. Baita, “Machine Learning-Based Sentiment Analysis on Twitter ( X ): A Case Study of the ‘ Kabur Aja Dulu ’ Issue Using SVM,” J. Appl. informatics Comput., vol. 9, no. 4, pp. 1972–1983, 2025.
[16] F. Wajidi and A. A. A. Cirua, “ANALISIS SENTIMEN ULASAN APLIKASI WONDR BY BNI MENGGUNAKAN ALGORITMA SVM DENGAN OPTIMASI KERNEL TRICK,” J. Ilm. Tek. dan Ilmu Komput., vol. 4, no. 2, pp. 69–81, 2025.
[17] S. R. Putri, M. Arifin, P. Studi, S. Informasi, F. Teknik, and U. M. Kudus, “Analisis Sentimen Publik terhadap Nadiem Makarim sebagai Mendikbudrisktek menggunakan Support Vector Machine ( SVM ),” Sist. Sist. Inf., vol. 14, pp. 826–834, 2025.
[18] F. R. Andhika, W. Witanti, and P. N. Sabrina, “Analisis Sentimen Menggunakan Metode IndoBERT pada Ulasan Aplikasi Zoom Menggunakan Fitur Ekstrasi GloVe,” Metik J., 2025, doi: 10.47002/metik.v9i2.1098.
[19] P. Arsi and R. Waluyo, “ANALISIS SENTIMEN WACANA PEMINDAHAN IBU KOTA INDONESIA MENGGUNAKAN ALGORITMA SUPPORT VECTOR MACHINE ( SVM ),” J. Teknol. Inf. dan ilmu Komput., vol. 8, no. 1, pp. 147–156, 2021, doi: 10.25126/jtiik.202183944.
[20] A. Septini, “Analisis Sentimen Masyarakat di Twitter Mengenai Open AI CHATGPT Menggunakan Metode Support Vector Machine ( SVM ),” Bull. Comput. Sci. Res., vol. 5, no. 2, pp. 138–149, 2025, doi: 10.47065/bulletincsr.v5i2.475.
[21] H. Tuhuteru, “Analisis Sentimen Masyarakat Terhadap Pembatasan Sosial Berksala Besar Menggunakan Algoritma Support Vector Machine,” Inf. Syst. Dev., vol. 4, no. 1, 2020.
[22] M. Lstm-rnn, Y. J. Juliansyah, and A. M. Hilda, “Analisis Sentimen Penggunaan Artificial Intelligence Terhadap Penyelenggaraan Pemilu 2024 Menggunakan Metode LSTM-RNN,” J. Inf. Syst. Res., vol. 6, no. 1, pp. 566–575, 2024, doi: 10.47065/josh.v6i1.6069.
[23] N. A. Maulana and D. Darwis, “Perbandingan Metode SVM dan Naïve Bayes untuk Analisis Sentimen pada Twitter tentang Obesitas di Kalangan Gen Z,” J. Pendidik. dan Teknol. Indones., vol. 5, no. 3, pp. 655–666, 2025.
[24] M. H. Arfian et al., “Analisis Sentimen Pada Media Sosial Menggunakan Metode Support Vector Machine,” JITKOM, vol. 09, no. 01, pp. 1–6, 2025, doi: 10.22441/jitkom.v9i1.001.
[25] F. Rachmawati, U. Azmi, and R. Azwarini, “Comparison of Lexicon-based Methods and Bidirectional Encoder Representations for Transformers Models in Sentiment Analysis of Government Debt Market Movements,” Int. J. Eng. Comput. Sci. Appl., vol. 4, no. 1, pp. 13–28, 2025.
[26] A. Yusupa and V. Tarigan, “PERBANDINGAN ALGORITMA MACHING LEARNING DALAM ANALISIS SENTIMEN MOBIL LISTRIK DI INDONESIA PADA MEDIA SOSIAL TWITTER / X,” JIP(Jurnal Inform. Polinema), vol. 10, edisi, pp. 479–490, 2023.
[27] A. Maulana, I. K. Afifah, A. Mubarrak, and K. R. Fauzan, “COMPARISON OF LOGISTIC REGRESSION , MULTINOMIALNB , SVM , AND K-NN METHODS ON SENTIMENT ANALYSIS OF GOJEK APP REVIEWS ON THE GOOGLE PLAY STORE,” J. Tek. Inform., vol. 4, no. 6, pp. 1487–1494, 2023.
[28] D. Komalla, R. G. G. Alam, and A. Wijaya, “Analisis Performa Algoritma Naïve Bayes dan SVM Menggunakan Python Pada Ulasan Sentimen Game Roblox,” J. Ris. Komput., vol. 12, no. 6, pp. 1036–1048, 2025, doi: 10.30865/jurikom.v12i6.9396.
[29] J. A. Wibowo, V. C. Mawardi, and T. Sutrisno, “VISUALISASI WORD CLOUD HASIL ANALISIS SENTIMEN BERBASIS FITUR LAYANAN APLIKASI GOJEK DENGAN SUPPORT VECTOR MACHINE,” J. Serina Sains, Tek. dan Kedokt., vol. 02, no. 01, pp. 61–70, 2024.
