Analisis Sentimen Publik terhadap Program Tabungan Perumahan Rakyat Menggunakan Model IndoBERT Lite pada Komentar YouTube
Public Sentiment Analysis of the Public Housing Savings Program Using the IndoBERT Lite Model on YouTube Comments
Keywords:
Analisis Sentimen, IndoBERT Lite Large, Media Sosial, TAPERAAbstract
Di era digital, media sosial menjadi platform utama bagi masyarakat menyampaikan opini terhadap kebijakan publik, termasuk Public Housing Savings (TAPERA), program pemerintah untuk menyediakan akses perumahan bagi masyarakat berpenghasilan rendah. Penelitian ini menganalisis sentimen masyarakat terhadap TAPERA menggunakan model IndoBERT Lite Large, yang dioptimalkan untuk data besar dengan efisiensi sumber daya. Dari 14.618 komentar YouTube yang dikumpulkan, 13.766 komentar diproses setelah tahap preprocessing. Hasil pelabelan sentimen menunjukkan dominasi sentimen negatif dengan 9.571 komentar, mencerminkan keresahan terhadap transparansi, implementasi, dan komunikasi program. Sentimen positif mencapai 2.485 komentar, menunjukkan apresiasi terbatas terhadap program, sementara sentimen netral sebanyak 1.710 komentar mengindikasikan kebutuhan informasi yang lebih jelas. Visualisasi menggunakan grafik batang dan word cloud menyoroti pola sentimen dan kata kunci yang sering muncul. Berdasarkan evaluasi menggunakan confusion matrix, model ini mencapai akurasi sebesar 78%. Meskipun efektif menangani data besar, penelitian ini memiliki keterbatasan dalam evaluasi performa model lebih mendalam. Penelitian selanjutnya disarankan untuk memperluas analisis dengan data dari berbagai platform media sosial agar meningkatkan analisis sentimen secara keseluruhan.
References
S. Gilbert, K. Shilton, and J. Vitak, “When research is the context: Cross-platform user expectations for social media data reuse,” Big Data Soc., vol. 10, no. 1, 2023, doi: 10.1177/20539517231164108.
M. Naeem, “Understanding the role of social media in organizational change implementation,” Manag. Res. Rev., vol. 43, no. 9, pp. 1097–1116, 2020, doi: 10.1108/MRR-07-2019-0336.
D. Darwis, N. Siskawati, and Z. Abidin, “Penerapan Algoritma Naive Bayes Untuk Analisis Sentimen Review Data Twitter Bmkg Nasional,” J. Tekno Kompak, vol. 15, no. 1, p. 131, 2021, doi: 10.33365/jtk.v15i1.744.
R. Abidin and A. Herawati, “Analisis Sentimen Publik Terhadap Kebijakan Program Tabungan Perumahan Rakyat (Tapera),” J. Inf. Syst. Comput., vol. 4, no. 1, pp. 13–19, 2024, doi: 10.34001/jister.v4i1.1002.
S. Thomas, Yuliana, and Noviyanti. P, “Study Analisis Metode Analisis Sentimen pada YouTube,” J. Inf. Technol., vol. 1, no. 1, pp. 1–7, 2021, doi: 10.46229/jifotech.v1i1.201.
J. E. Tang, V. Arvind, C. Dominy, C. A. White, S. K. Cho, and J. S. Kim, “How Are Patients Reviewing Spine Surgeons Online? A Sentiment Analysis of Physician Review Website Written Comments,” Glob. Spine J., vol. 13, no. 8, pp. 2107–2114, 2023, doi: 10.1177/21925682211069933.
T. D. Purnomo, J. Sutopo, and A. History, “Comparison Of Pre-Trained Bert-Based Transformer Models For Regional,” vol. 3, no. 3, pp. 11–21, 2024, doi: 10.56127/ijst.v3i3.1739.
Anugerah Simanjuntak et al., “Research and Analysis of IndoBERT Hyperparameter Tuning in Fake News Detection,” J. Nas. Tek. Elektro dan Teknol. Inf., vol. 13, no. 1, pp. 60–67, 2024, doi: 10.22146/jnteti.v13i1.8532.
B. A. Setyawan, Analisis sentimen multilabel terhadap ujaran kebencian menggunakan gabungan metode indo bert lite dan bidirectional lstm-cnn dengan grid search hyperparameter optimization, no. 11180910000102. Fakultas Sains dan Teknologi UIN Syarif HIdayatullah Jakarta, 2024. [Online]. Available: https://repository.uinjkt.ac.id/dspace/handle/123456789/77089
I. D. A. N. I. Pada, “Perbandingan Kinerja Pre-Trained Tokopedia Seller Center,” vol. 11, no. 2, pp. 13–20, 2024, doi: 10.30656/jsii.v11i2.9168.
B. Richardson and A. Wicaksana, “Comparison of Indobert-Lite and Roberta in Text Mining for Indonesian Language Question Answering Application,” Int. J. Innov. Comput. Inf. Control, vol. 18, no. 6, pp. 1719–1734, 2022, doi: 10.24507/ijicic.18.06.1719.
S. Imron, E. I. Setiawan, and J. Santoso, “Deteksi Aspek Review E-Commerce Menggunakan IndoBERT Embedding dan CNN,” J. Intell. Syst. Comput., vol. 5, no. 1, pp. 10–16, 2023, doi: 10.52985/insyst.v5i1.267.
R. W. Hardian, P. E. Prasetyo, U. Khaira, and T. Suratno, “Analisis Sentiment Kuliah Daring Di Media Sosial Twitter Selama Pandemi Covid-19 Menggunakan Algoritma Sentistrength,” MALCOM Indones. J. Mach. Learn. Comput. Sci., vol. 1, no. 2, pp. 138–143, 2021, doi: 10.57152/malcom.v1i2.15.
C. A. A. Soemedhy, N. Trivetisia, N. A. Winanti, D. P. Martiyaningsih, T. W. Utami, and S. Sudianto, “Analisis Komparasi Algoritma Machine Learning untuk Sentiment Analysis (Studi Kasus: Komentar YouTube ‘Kekerasan Seksual’),” J. Inform. J. Pengemb. IT, vol. 7, no. 2, pp. 80–84, 2022, doi: 10.30591/jpit.v7i2.3547.
P. Y. Saputra, D. H. Subhi, and Fahmi Zain Afif Winatama, “Implementasi Sentimen Analisis Komentar Channel Video Pelayanan Pemerintah Di Youtube Menggunakan Algoritma Naïve Bayes,” J. Inform. Polinema, vol. 5, no. 4, pp. 209–213, 2019, doi: 10.33795/jip.v5i4.259.
N. Hendrastuty, A. Rahman Isnain, and A. Yanti Rahmadhani, “Analisis Sentimen Masyarakat Terhadap Program Kartu Prakerja Pada Twitter Dengan Metode Support Vector Machine,” J. Inform. J. Pengemb. IT, vol. 6, no. 3, pp. 150–155, 2021, doi: 10.30591/jpit.v6i3.2870.
D. Rifaldi, Abdul Fadlil, and Herman, “Teknik Preprocessing Pada Text Mining Menggunakan Data Tweet ‘Mental Health,’” Decod. J. Pendidik. Teknol. Inf., vol. 3, no. 2, pp. 161–171, 2023, doi: 10.51454/decode.v3i2.131.
A. B. Putra Negara, “The Influence Of Applying Stopword Removal And Smote On Indonesian Sentiment Classification,” Lontar Komput. J. Ilm. Teknol. Inf., vol. 14, no. 3, p. 172, 2023, doi: 10.24843/lkjiti.2023.v14.i03.p05.
M. U. Albab, Y. Karuniawati P, and M. N. Fawaiq, “Optimization of the Stemming Technique on Text preprocessing President 3 Periods Topic,” J. Transform., vol. 20, no. 2, pp. 1–10, 2023, doi: 10.26623/transformatika.v20i2.5374.
C. T. Yuang, R. E. Banchs, and C. E. Siong, “An Empirical Evaluation of Stop Word Removal in Statistical Machine Translation,” Jt. Work. Exploit. Synerg. between Inf. Retr. Mach. Transl. ESIRMT 2012 Hybrid Approaches to Mach. Transl. HyTra 2012 Eur. Chapter Assoc. Comput. Linguist. EACL 2012 - Procee, no. January, pp. 30–37, 2012, [Online]. Available: https://api.semanticscholar.org/CorpusID:302123
F. Arifadilah et al., Perbandingan Hyperparameter Optimization Population Based Training, Random Search, Bayesian Optimization Pada Analisis Sentimen Radikalisme. Fakultas Sains dan Teknologi UIN Syarif HIdayatullah Jakarta, 2023. [Online]. Available: https://repository.uinjkt.ac.id/dspace/handle/123456789/76873
M. Y. Ridho and E. Yulianti, “From Text to Truth?: Leveraging IndoBERT and Machine Learning Models for Hoax Detection in Indonesian News,” vol. 10, no. 3, pp. 544–555, 2024, doi: 10.26555/jiteki.v10i3.29450.
N. K. Nissa and E. Yulianti, “Multi-label text classification of Indonesian customer reviews using bidirectional encoder representations from transformers language model,” Int. J. Electr. Comput. Eng., vol. 13, no. 5, pp. 5641–5652, 2023, doi: 10.11591/ijece.v13i5.pp5641-5652.
N. Shahid, M. U. Ilyas, J. S. Alowibdi, and N. R. Aljohani, “Word cloud segmentation for simplified exploration of trending topics on Twitter,” IET Softw., vol. 11, no. 5, pp. 214–220, 2017, doi: 10.1049/iet-sen.2016.0307.
J. Zhou, A. H. Gandomi, F. Chen, and A. Holzinger, “Evaluating the quality of machine learning explanations: A survey on methods and metrics,” Electron., vol. 10, no. 5, pp. 1–19, 2021, doi: 10.3390/electronics10050593.
R. Indransyah, Y. H. Chrisnanto, P. N. Sabrina, and S. Kom, “Klasifikasi Sentimen Pergelaran MotoGP di Indonesia Menggunakan Algoritma Correlated Naive Bayes Clasifier,” INFOTECH J., vol. 8, no. 2, pp. 60–66, 2022, doi: 10.31949/infotech.v8I2.3103.
B. IANCU, “Web Crawler for Indexing Video e-Learning Resources: A YouTube Case Study,” Inform. Econ., vol. 23, no. 2/2019, pp. 15–24, 2019, doi: 10.12948/issn14531305/23.2.2019.02.
