Perbandingan Kinerja Model Probabilistic, Linear Model, Instance-Based, dan Ensemble Learning (Studi Kasus: Ulasan Google Playstore Aplikasi Threads)
DOI:
https://doi.org/10.47111/jointecoms.v6i1.25770Keywords:
Threads, Machine Learning, SentimenAbstract
Pertumbuhan Threads sebagai media sosial baru memunculkan kebutuhan akan pemahaman sentimen pengguna. Ulasan di Google Play Store menjadi sumber penting untuk menangkap persepsi publik terhadap fitur dan performa aplikasi. Sebagai platform yang masih berkembang, Threads menyediakan peluang strategis bagi pengembang untuk merespons masukan secara tepat. Namun, besarnya volume dan format ulasan yang tidak seragam menyulitkan proses analisis secara manual. Penelitian ini membandingkan kinerja empat algoritma Naïve Bayes (probabilistic), SVM (linear), K-NN (instance-based), dan Random Forest (ensemble) dalam klasifikasi sentimen ulasan Threads. Penelitian ini dimulai dengan studi literatur dan pengumpulan data ulasan Threads melalui scraping. Dilabeli menggunakan IndoBERT, proses preprocessing mencakup remove duplicate, cleaning, normalization, tokenization, stopwords dan lemmatization, diekstraksi dengan TF-IDF, diseimbangkan memakai SMOTE, lalu dibagi 80:20 untuk latih dan uji. Evaluasi mencakup akurasi, presisi, recall, F1-score, serta waktu pelatihan dan prediksi. Hasil menunjukkan Random Forest menjadi algoritma terbaik (akurasi 81,8%; F1-score 76,6%), disusul SVM (81,4%; 75,9%), Naïve Bayes (79,1%; 72,4%), dan K-NN (61,2%; 57,6%). Random Forest unggul hampir di semua metrik, SVM efisien dengan performa seimbang, Naïve Bayes menonjol pada kecepatan, sementara K-NN lambat pada prediksi. Untuk implementasi, dibangun dashboard interaktif berbasis Streamlit guna memvisualisasikan perkembangan dan prediksi sentimen pengguna Threads.
Downloads
References
[1] T. Ongun, "Pengguna Threads capai 100 juta dalam 5 hari setelah diluncurkan," Anadolu Agency, Jul. 11, 2023. [Online]. Available: https://www.aa.com.tr/id/dunia/pengguna-Threads-capai-100-juta-dalam-5-hari-setelah-diluncurkan/2942356. [Accessed: Apr. 25, 2025].
[2] Mashable Indonesia, "Threads raih 20 juta pengguna bulanan baru, total mencapai 320 juta," Mashable Indonesia, Feb. 26, 2025. [Online]. Available: https://id.mashable.com/tech/6632/Threads-raih-20-juta-pengguna-bulanan-baru-total-mencapai-320-juta. [Accessed: Feb. 5, 2025].
[3] Influencer Marketing Hub, "Comparing X (Twitter) and Threads to understand the difference," Nov. 29, 2024. [Online]. Available: https://influencermarketinghub.com/x-twitter-Threads/. [Accessed: May 16, 2025].
[4] R. Montti, "Threads: What is the new social app from Instagram?" Search Engine Journal, Oct. 8, 2024. [Online]. Available: https://www.searchenginejournal.com/Threads/493069/. [Accessed: Aug. 8, 2025].
[5] E. D. Madyatmadja, H. Candra, J. Nathaniel, and M. R. Jonathan, "Sentiment Analysis on User Reviews of Threads Applications in Indonesia," Journal Européen des Systèmes Automatisés, vol. 57, no. 4, p. 1165, 2024. [Online]. Available: https://www.proquest.com/openview/7ca13f2eb65a75ef65a2ffca2c340b76/1?cbl=2069456&pq-origsite=gscholar. [Accessed: Apr. 25, 2025].
[6] A. Nadira, N. Y. Setiawan, and W. Purnomo, "Analisis Sentimen Pada Ulasan Aplikasi Mobile Banking Menggunakan Metode Naïve Bayes Dengan Kamus Inset," Indexia, vol. 5, no. 1, pp. 35–47, 2023. [Online]. Available: —. [Accessed: July. 5, 2025].
[7] M. A. Java, M. Syafrullah, W. Windarto, and P. Painem, "Analisis Sentimen Ulasan Pengguna Aplikasi Threads pada Google Play Store Menggunakan Multinomial Naïve Bayes dan Support Vector Machine," Jurnal Ticom: Technology of Information and Communication, vol. 12, no. 2, pp. 75–80, 2024. [Online]. Available: https://jurnal-ticom.jakarta.aptikom.org/index.php/Ticom/article/view/112/91. [Accessed: Apr. 25, 2025].
[8] N. Wulandari, Y. Cahyana, R. Rahmat, and H. Hikmayanti, "Sentiment Analysis on the Relocation of the National Capital (IKN) on Social Media X Using Naive Bayes and K-Nearest Neighbor (KNN) Methods," Journal of Applied Informatics and Computing, vol. 9, no. 3, pp. 724–731, 2025. [Online]. Available: https://jurnal.polibatam.ac.id/index.php/JAIC/article/view/9552/2768. [Accessed: Jul. 9, 2025].
[9] J. Muliawan and E. Dazki, "Sentiment Analysis of Indonesia's Capital City Relocation using Three Algorithms: Naïve Bayes, KNN, and Random Forest," Jurnal Teknik Informatika (JUTIF), vol. 4, no. 5, pp. 1227–1236, 2023. [Online]. Available: https://pdfs.semanticscholar.org/71d2/6332c2d30b7cb91a356e7cda9e1327e0590d.pdf. [Accessed: Jul. 5, 2025].
[10] R. Khairunnas, J. A. Pagua, G. Fitriya, and Y. Ruldeviyani, "User sentiment dynamics in social media: a comparative analysis of X and Threads," IAES International Journal of Artificial Intelligence, vol. 14, no. 1, pp. 447–456, 2025. [Online]. Available: https://www.researchgate.net/publication/388598598_User_sentiment_dynamics_in_social_media_a_comparative_analysis_of_X_and_Threads. [Accessed: May 1, 2025].
[11] F. Nufairi, N. Pratiwi, and F. Herlando, "Analisis Sentimen Pada Ulasan Aplikasi Threads Di Google Playstore Menggunakan Algoritma Support Vector Machine," JIPI (Jurnal Ilmiah Penelitian dan Pembelajaran Informatika), vol. 9, no. 1, pp. 339–348, 2024. [Online]. Available: https://jurnal.stkippgritulungagung.ac.id/index.php/jipi/article/view/4929. [Accessed: Feb. 5, 2025].
[12] M. P. Pulungan, A. Purnomo, and A. Kurniasih, "Penerapan SMOTE untuk Mengatasi Imbalance Class dalam Klasifikasi Kepribadian MBTI Menggunakan Naïve Bayes Classifier," Jurnal Teknologi Informasi dan Ilmu Komputer, vol. 11, no. 5, pp. 1033–1042, 2024. [Online]. Available: https://www.researchgate.net/publication/376959015_Penerapan_SMOTE_untuk_Mengatasi_Imbalance_Class_dalam_Klasifikasi_Kepribadian_MBTI_Menggunakan_Naive_Bayes_Classifier. [Accessed: Feb. 11, 2025].
[13] ProjectPro, "Probabilistic Models in Machine Learning," ProjectPro, 2024. [Online]. Available: https://www.projectpro.io/article/probabilistic-models-in-machine-learning/784. [Accessed: Apr. 25, 2025].
[14] F. T. Berton, D. E. Ratnawati, and M. A. Rahman, "Perbandingan Naïve Bayes Dan K-Nearest Neighbor Untuk Analisis Sentimen Terhadap Ulasan Aplikasi Threads," Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer, vol. 8, no. 9, 2023. [Online]. Available: https://j-ptiik.ub.ac.id/index.php/j-ptiik/article/view/14109/6301. [Accessed: Apr. 25, 2025].
[15] A. S. Nabila, "Perbandingan Model Machine Learning Dan Deep Learning Terhadap Analisis Sentimen Pelanggan Shopee," Doctoral dissertation, UIN Ar-Raniry Banda Aceh, 2024. [Online]. Available: https://repository.ar-raniry.ac.id/id/eprint/37469/1/Alissa%20Sausan%20Nabila,%20190705057,%20FST,%20TI.pdf. [Accessed: Jul. 5, 2025].
[16] BINUS School of Information Systems, "Description and application of Linear and non-Linear in data mining," BINUS School of Information Systems, Jan. 28, 2022. [Online]. Available: https://sis.binus.ac.id/2022/01/28/description-and-application-of-linear-and-non-linear-in-data-mining-2/. [Accessed: May 1, 2025].
[17] Kirim.ai, "Model Linear: Regresi Linear, Regresi Logistik, dan SVM," Kirim.ai, 2025. [Online]. Available: https://hub.kirim.ai/model-linear-regresi-linear-logistik-SVM/. [Accessed: Aug. 13, 2025].
[18] A. H. Iman, F. R. Permana, G. P. Wardana, R. K. Rachmansyah, and M. M. Santoni, "Perbandingan Algoritma Klasifikasi Random Forest dan Extreme Gradient Boosting pada Dataset Cuaca Provinsi DKI Jakarta Tahun 2018," in Prosiding Seminar Nasional Mahasiswa Bidang Ilmu Komputer dan Aplikasinya, vol. 3, no. 2, pp. 793–803, Aug. 2022. [Online]. Available: https://conference.upnvj.ac.id/index.php/senamika/article/view/2218/1691. [Accessed: Aug. 13, 2025].
[19] GeeksforGeeks, "Random Forest Algorithm in Machine Learning," GeeksforGeeks, Jan. 16, 2025. [Online]. Available: https://www.geeksforgeeks.org/machine-learning/random-forest-algorithm-in-machine-learning/. [Accessed: May 1, 2025].
[20] GeeksforGeeks, "Lemmatization vs Stemming: A deep dive into NLP’s text Normalization techniques," GeeksforGeeks, n.d. [Online]. Available: https://www.geeksforgeeks.org/lemmatization-vs-stemming-a-deep-dive-into-NLPs-text-Normalization-techniques/#what-is-lemmatization. [Accessed: Apr. 30, 2025].
[21] GeeksforGeeks, "What is data Cleaning?" GeeksforGeeks, n.d. [Online]. Available: https://www.geeksforgeeks.org/what-is-data-Cleaning/#2-removing-duplicates. [Accessed: Apr. 30, 2025].
[22] T. M. Mitchell, Machine Learning. McGraw-Hill, 1997. [Online]. Available: https://www.cs.swarthmore.edu/~meeden/cs63/s16/reading/Mitchell_ch8.pdf. [Accessed: Aug. 13, 2025].
[23] M. D. Maulidan, S. Sumarlinda, and S. Sopingi, "Development of Sentimen Analysis System of Simple Pol Application on Google Playstore Using Naïve Bayes Classifier Method and BERT Prediction," Journal of Dinda: Data Science, Information Technology, and Data Analytics, vol. 4, no. 2, pp. 115–122, 2024. [Online]. Available: https://journal.ittelkom-pwt.ac.id/index.php/dinda/article/view/1577/507. [Accessed: Feb. 5, 2025].
[24] M. E. Purbaya, D. P. Rakhmadani, M. P. Arum, and L. Z. Nasifah, "Implementation of N-Gram Methodology to Analyze Sentiment Reviews for Indonesian Chips Purchases in Shopee E-Marketplace," Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi), vol. 7, no. 3, pp. 609–617, 2023. [Online]. Available: https://www.researchgate.net/publication/371281311_Implementation_of_N-Gram_Methodology_to_Analyze_Sentiment_Reviews_for_Indonesian_Chips_Purchases_in_Shopee_E-Marketplace. [Accessed: Aug. 19, 2025].
[25] H. Basri, M. B. S. Junianto, and I. Kusyadi, "Enhancing usability testing through sentiment analysis: A comparative study using SVM, Naïve Bayes, Decision Trees and Random Forest," Jurnal Teknik Informatika dan Sistem Informasi, Univ. Pamulang, 2024. [Online]. Available: https://openjournal.unpam.ac.id/index.php/JTSI/article/view/45117. [Accessed: Aug. 16, 2025].
[26] G. K. Putri, H. Sujaini, and D. I. Ulumi, "Perbandingan Algoritma Support Vector Machine (SVM) dan Naive Bayes pada Analisis Sentimen Bahasa Jawa dan Sunda," JUSTIN (Jurnal Sistem dan Teknologi Informasi), vol. 13, no. 2, pp. 299–306, 2025. [Online]. [Accessed: Aug. 16, 2025].
[27] A. N. K. Kambayo, S. S. Berutu, J. Jatmika, and A. Nshimiyimana, "Aspect-Based Sentiment Analysis Using Latent Dirichlet Allocation (LDA) and DistilBERT on Threads App Reviews," Infact: International Journal of Computers, vol. 9, no. 1, pp. 25–34, 2025. [Online]. Available: https://journal.ukrim.ac.id/index.php/JIF/article/view/707/527. [Accessed: Aug. 20, 2025].
[28] M. F. Hanif, S. H. Wijoyo, and W. H. N. Putra, "Klasifikasi Sentimen Ulasan Aplikasi Threads Berbasis Algoritma Naive Bayes dan Metode Root Caus Analysis," Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer, vol. 8, no. 6, 2024. [Online]. Available: https://j-ptiik.ub.ac.id/index.php/j-ptiik/article/view/13786/6131. [Accessed: Aug. 20, 2025].
[29] I. A. I. Pidada and N. P. N. C. Dewi, "The Effect of User Interface, User Experience, and Perceived Ease of Use on Interest in Using the SOCO by Sociolla Application with Perceived Usefulness as a Moderator," Golden Ratio of Marketing and Applied Psychology of Business, vol. 5, no. 1, pp. 234–245, 2025. [Online]. [Accessed: Aug. 20, 2025].
[30] N. M. Damayanti, "Analisis Sentimen Publik Pada Tagar #Btscomeback Di Platform X Menggunakan IndoBERTweet," Jurnal Informatika dan Teknik Elektro Terapan, vol. 13, no. 3, 2025. [Online]. [Accessed: Aug. 20, 2025].
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Journal of Information Technology and Computer Science
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
