eprintid: 58484 rev_number: 31 eprint_status: archive userid: 18179 dir: disk0/00/05/84/84 datestamp: 2026-02-18 07:48:41 lastmod: 2026-02-18 07:48:41 status_changed: 2026-02-18 07:48:41 type: thesis metadata_visibility: show contact_email: julkifli.jul26@gmail.com creators_name: JULKIFLI, JULKIFLI creators_id: 3337210026 contributors_type: http://www.loc.gov/loc.terms/relators/THS contributors_type: http://www.loc.gov/loc.terms/relators/THS contributors_name: Hardiansyah, Alim contributors_name: Ansori, Yulian contributors_id: 198202162023211014 contributors_id: 199007222024061001 corp_creators: UNIVERSITAS SULTAN AGENG TIRTAYASA corp_creators: FAKULTAS TEKNIK corp_creators: JURUSAN INFORMATIKA title: ANALISIS SENTIMEN TWITTER TERHADAP APLIKASI MYTELKOMSEL MENGGUNAKAN MODEL BIDIRECTIONAL LONG SHORT-TERM MEMORY (BILSTM) ispublished: pub subjects: QA75 subjects: QA76 subjects: T1 divisions: TKI full_text_status: restricted note: Evaluasi kepuasan pengguna terhadap aplikasi MyTelkomsel seringkali terkendala oleh keterbatasan jangkauan metode survei konvensional yang tidak mampu menangkap respons pengguna secara waktu nyata. Penelitian ini bertujuan untuk menganalisis sentimen publik berskala nasional menggunakan metode Deep Learning dengan arsitektur Bidirectional Long Short-Term Memory (Bi-LSTM). Data ulasan dikumpulkan melalui teknik web scraping menggunakan perangkat lunak Tweet-Harvest dan dilabeli secara otomatis melalui pendekatan Ensemble Learning berbasis Transformer (IndoBERT, RoBERTa, dan BERT-SMSA) untuk mengatasi ketiadaan label pada data mentah. Model klasifikasi yang dikembangkan mengintegrasikan fitur Word Embedding FastText guna menangani karakteristik bahasa tidak baku dan kata-kata di luar kosakata (OOV) yang dominan di media sosial. Hasil pengujian menggunakan metode Stratified 5-Fold Cross Validation menunjukkan bahwa model yang diusulkan mampu mencapai akurasi rata-rata sebesar 96%, dengan nilai F1-Score pada kelas negatif mencapai 93%. Penelitian ini menyimpulkan bahwa kombinasi arsitektur Bi-LSTM dan teknik pelabelan otomatis terbukti efektif dalam merepresentasikan sentimen pengguna secara akurat dan konsisten sebagai acuan strategis bagi pengembangan layanan abstract: User satisfaction evaluation of the MyTelkomsel application is often hindered by the limited scope of conventional survey methods, which fail to capture real-time user responses. This study aims to analyze national-scale public sentiment using a Deep Learning method with Bidirectional Long Short-Term Memory (Bi-LSTM) architecture. Review data was collected via web scraping techniques using Tweet Harvest software and automatically labeled through a Transformer-based Ensemble Learning approach (IndoBERT, RoBERTa, and BERT-SMSA) to address the lack of labels in raw data. The developed classification model integrates FastText Word Embedding features to handle informal language characteristics and out-of vocabulary (OOV) words dominant in social media. Testing results using the Stratified 5-Fold Cross Validation method showed that the proposed model achieved an average accuracy of 96%, with an F1-Score of 93% on the negative class. This study concludes that the combination of Bi-LSTM architecture and automatic labeling techniques proves effective in accurately and consistently representing user sentiment as a strategic reference for service development. date: 2026-02-18 date_type: published pages: 78 institution: Fakultas Teknik Universitas Sultan Ageng Tirtayasa department: INFORMATIKA thesis_type: sarjana thesis_name: sarjana referencetext: [1] R. Joshi, N. Pavithra, and C. K. Singh, “Internet an Integral Part of Human Life in 21st Century: A Review,” Curr. J. Appl. Sci. Technol., vol. 41, no. 36, pp. 12–18, 2022, doi: 10.9734/cjast/2022/v41i363963. [2] D. K. K, “Social Media and Social Networking,” Interantional J. Sci. Res. Eng. Manag., vol. 08, no. 03, pp. 1–5, 2024, doi: 10.55041/ijsrem29635. [3] Muhammad Iqbal, Ali Mustopa, Wahyu Nugraha, Umi Khultsum, and Rabiatus Sa’adah, “Cerdas Dan Bijak Menggunakan Media Sosial Terhadap Keamanan Informasi Di Era Digital Pada Kelompok Wanita Tani Melati,” J. Penelit. dan Pengabdi. Masy. Jotika, vol. 2, no. 2, pp. 26–30, 2023, doi: 10.56445/jppmj.v2i2.67. [4] A. Rivaldy, H. A. Fedria Wowor, S. R. Maisya, and D. Safitri, “PENGGUNAAN TWITTER DALAM MENINGKATKAN MELEK POLITIK MAHASISWA ILMU KOMUNIKASI UNIVERSITAS NEGERI JAKARTA,” Perspekt. Komun. J. Ilmu Komun. Polit. dan Komun. Bisnis, vol. 5, no. 1, p. 41, Jun. 2021, doi: 10.24853/pk.5.1.41-48. [5] H. C. Husada and A. S. Paramita, “Analisis Sentimen Pada Maskapai Penerbangan di Platform Twitter Menggunakan Algoritma Support Vector Machine (SVM),” Teknika, vol. 10, no. 1, pp. 18–26, 2021, doi: 10.34148/teknika.v10i1.311. [6] I. S. K. Idris, Y. A. Mustofa, and I. A. Salihi, “Analisis Sentimen Terhadap Penggunaan Aplikasi Shopee Mengunakan Algoritma Support Vector Machine (SVM),” Jambura J. Electr. Electron. Eng., vol. 5, no. 1, pp. 32– 35, 2023, doi: 10.37905/jjeee.v5i1.16830. [7] K. T. Nugroho, B. Julianto, and D. F. Nur MS, “Usability Testing pada Sistem Informasi Manajemen AKN Pacitan Menggunakan Metode System Usability Scale,” J. Nas. Pendidik. Tek. Inform., vol. 11, no. 1, p. 74, 2022, doi: 10.23887/janapati.v11i1.43209. [8] C. K. Poetra, S. F. Pane, and N. S. Fatonah, “Meningkatkan Akurasi Long￾Short Term Memory (LSTM) pada Analisis Sentimen Vaksin Covid-19 di Twitter dengan Glove,” J. Telemat., vol. 16, no. 2, pp. 85–90, 2022, doi: 10.61769/telematika.v16i2.400. 57 [9] M. Haerunnissa, A. Priyanto, C. Asnawi, and N. Alfi Sa’diya, “Analisis Sentimen Kepuasan Pelanggan Perusahaan Telekomunikasi Seluler Telkomsel di Twitter,” Teknomatika J. Inform. dan Komput., vol. 15, no. 2, pp. 68–75, 2022, doi: 10.30989/teknomatika.v15i2.1117. [10] A. Hardiansyah and L. Judijanto, “Artificial Intelligence and Machine Learning in Personalisation Marketing: a Literature Review,” Rev. Int. Econ. Financ., vol. 1, no. 3, pp. 137–143, 2025. [11] C. B. Vennerød, A. Kjærran, and E. S. Bugge, “Long Short-term Memory RNN,” May 2021, [Online]. Available: http://arxiv.org/abs/2105.06756 [12] A. A. Ningrum, I. Syarif, A. I. Gunawan, E. Satriyanto, and R. Muchtar, “Algoritma Deep Learning-Lstm Untuk Memprediksi Umur Deep Learning￾Lstm Algorithm for Power Transformer Lifetime,” J. Teknol. Inf. dan Ilmu Komput., vol. 8, no. 3, pp. 539–548, 2021, doi: 10.25126/jtiik.202184587. [13] H. B. Wahari, S. Asmal, and K. Amar, “Analysis of Factors Influencing the Usage of Mytelkomsel Application in Makassar,” J. Ind. Eng. Manag., vol. 8, no. 2, pp. 157–166, 2023, doi: 10.33536/jiem.v8i2.1742. [14] B. Kurniawan, A. Suwarisman, I. Afriyanti, A. Wahyudi, and D. D. Saputra, “Analisis Sentimen Complain dan Bukan Complain pada Twitter Telkomsel dengan SMOTE dan Naïve Bayes,” J. JTIK (Jurnal Teknol. Inf. dan Komunikasi), vol. 7, no. 1, pp. 106–113, 2023, doi: 10.35870/jtik.v7i1.691. [15] T. I. Cahyani, W. Gata, D. D. Saputra, H. B. Novitasari, and H. Hernawati, “Analisis Sentimen Terhadap Telkomsel dan XL Berbasis Machine Learning Pada Data Twitter,” INTECOMS J. Inf. Technol. Comput. Sci., vol. 6, no. 1, pp. 265–274, 2023, doi: 10.31539/intecoms.v6i1.5765. [16] S. Jurnalis Pipin and H. Kurniawan, “Analisis Sentimen Kebijakan MBKM Berdasarkan Opini Masyarakat di Twitter Menggunakan LSTM,” J. SIFO Mikroskil, vol. 23, no. 2, pp. 197–208, 2022, doi: 10.55601/jsm.v23i2.900. [17] I. Pakpahan and Jasman Pardede, “Analisis Sentimen Penanganan Covid-19 Menggunakan Metode Long Short-Term Memory Pada Media Sosial Twitter,” J. Publ. Tek. Inform., vol. 2, no. 1, pp. 12–25, 2023, doi: 10.55606/jupti.v1i1.767. [18] N. H. Wardani, “Implementasi Web Crawling Untuk Mengumpulkan Tweets 58 Terkait Produk Perikanan Olahan Yang Diminati Masyarakat,” JFMR￾Journal Fish. Mar. Res., vol. 7, no. 2, 2023, doi: 10.21776/ub.jfmr.2023.007.02.3. [19] M. H. Al-Areef and K. Saputra S, “Analisis Sentimen Pengguna Twitter Mengenai Calon Presiden Indonesia Tahun 2024 Menggunakan Algoritma LSTM,” J. SAINTIKOM (Jurnal Sains Manaj. Inform. dan Komputer), vol. 22, no. 2, p. 270, 2023, doi: 10.53513/jis.v22i2.8680. [20] M. A. Khder, “Web Scraping or Web Crawling : State of Art , Techniques , Approaches and Application,” vol. 13, no. 3, 2021, doi: 10.15849/IJASCA.211128.11. [21] N. Suarna, W. Prihartono, T. Informatika, K. Akuntansi, and P. Store, “PENERAPAN NLP ( NATURAL LANGUAGE PROCESSING ) DALAM ANALISIS,” vol. 8, no. 2, pp. 1841–1846, 2024. [22] P. Bojanowski, E. Grave, A. Joulin, and T. Mikolov, “Enriching Word Vectors with Subword Information,” vol. 5, pp. 135–146, 2017. [23] D. Wungguli, N. I. Yahya, I. K. Hasan, and S. N. Abdussamad, “Implementasi Metode Bidirectional LSTM Dengan Word Embedding FastText Dalam Analisis Sentimen Ulasan Pengguna Aplikasi Maxim,” J. Ris. Mhs. Mat., vol. 4, no. 5, pp. 204–217, 2025, doi: 10.18860/jrmm.v4i5.33358. [24] F. Darnis, A. Rahman, and Y. Ansori, “Akurasi Model Algoritma Recurrent Neural Network untuk Prediksi Saham Syariah,” J. Teknomatika, vol. 15, no. 1, pp. 17–24, 2025. [25] Yulian Ansori, Arief Rahman, Febriyanti Darnis, and Miftahus Sholihin, “Peramalan Suhu Udara Menggunakan Algoritma Long Short Term Memory,” Inform. J. Tek. Inform. dan Multimed., vol. 5, no. 1, pp. 119–126, 2025, doi: 10.51903/informatika.v5i1.1033. [26] A. Rahman, Y. Ansori, F. Darnis, C. S. Azkia, and M. Sholihin, “Prediksi Harga Emas Aneka Tambang ( Antam ) Menggunakan Long Short- Term Memory ( LSTM ),” vol. 4, no. 4, pp. 1939–1945, 2025. [27] A. R. Gunawan and R. F. Alfa Aziza, “Sentiment Analysis Using LSTM Algorithm Regarding Grab Application Services in Indonesia,” J. Appl. 59 Informatics Comput., vol. 9, no. 2, pp. 322–332, 2025, doi: 10.30871/jaic.v9i2.8696. [28] P. Utami, M. R. Ningsih, D. A. A. Pertiwi, and J. Unjung, “Sentiment based�emotion classification using bidirectional long short term-memory (Bi�LSTM),” J. Soft Comput. Explor., vol. 5, no. 3, pp. 281–289, Sep. 2024, doi: 10.52465/joscex.v5i3.461. [29] S. Widodo, H. Brawijaya, and S. Samudi, “Stratified K-fold cross validation optimization on machine learning for prediction,” Sinkron, vol. 7, no. 4, pp. 2407–2414, Oct. 2022, doi: 10.33395/sinkron.v7i4.11792. [30] Indra Swanto Ritonga, Wanayumini, and Dedy Hartama, “Sentiment Classification in Imbalanced Data: Trade-Offs Between Metrics and Real�World Relevance,” J. Tek. Inform., vol. 18, no. 2, pp. 303–315, Oct. 2025, doi: 10.15408/jti.v18i2.46652. [31] S. Dewi, “Analisis Sentimen Aplikasi WhatsApp berdasarkan Ulasan di,” Arus J. Sains dan Teknol., vol. 2, no. 2, 2024. [32] H. T. Santoso, F. A. Felmidi, A. N. Fadhila, A. Ristyawan, and E. Daniati, “Analisis Kinerja Algoritma Data Mining pada Klasifikasi Tingkat Obesitas dengan K-Fold Cross Validation dan AUC,” Agustus, vol. 8, pp. 2549–7952, 2024, doi: https://doi.org/10.29407/inotek.v8i1.4917. citation: JULKIFLI, JULKIFLI (2026) ANALISIS SENTIMEN TWITTER TERHADAP APLIKASI MYTELKOMSEL MENGGUNAKAN MODEL BIDIRECTIONAL LONG SHORT-TERM MEMORY (BILSTM). S1 thesis, Fakultas Teknik Universitas Sultan Ageng Tirtayasa. document_url: https://eprints.untirta.ac.id/58484/1/Julkifli_3337210026_Fulltext.pdf document_url: https://eprints.untirta.ac.id/58484/2/Julkifli_3337210026_01.pdf document_url: https://eprints.untirta.ac.id/58484/3/Julkifli_3337210026_02.pdf document_url: https://eprints.untirta.ac.id/58484/5/Julkifli_3337210026_03.pdf document_url: https://eprints.untirta.ac.id/58484/6/Julkifli_3337210026_04.pdf document_url: https://eprints.untirta.ac.id/58484/7/Julkifli_3337210026_05.pdf document_url: https://eprints.untirta.ac.id/58484/8/Julkifli_3337210026_Ref.pdf document_url: https://eprints.untirta.ac.id/58484/9/Julkifli_3337210026_Lamp.pdf document_url: https://eprints.untirta.ac.id/58484/10/Julkifli_3337210026_CP.pdf