Utilization of Natural Language Processing (NLP) For The Analysis and Classification of Career Concern Topics Based on Tiktok Comments Using Support Vector Machine (SVM) With a Web-Based System

Natasya Maharani; Yohanni Syahra

doi:10.63922/ijeter.v4i03.6223

Natasya Maharani Program Studi Sistem Informasi Fakultas Ilmu Komputer Universitas Muhammadiyah Sumatera Utara Medan
Yohanni Syahra Program Studi Teknologi Informasi Fakultas Ilmu Komputer Universitas Muhammadiyah Sumatera Utara Medan

DOI: https://doi.org/10.63922/ijeter.v4i03.6223

Keywords: Career Concerns, Natural Language Processing, Social Media, Support Vector Machine, TikTok

Abstract

The rapid transformation of the labor market has increased the expression of career concerns through social media, including TikTok. This study aims to classify career concern topics in Indonesian-language TikTok comments using Natural Language Processing (NLP), Term Frequency-Inverse Document Frequency (TF-IDF), and Support Vector Machine (SVM), and to implement the resulting model in a web-based system. This quantitative study employed text mining and machine learning methods. The population comprised Indonesian-language TikTok comments concerning employment and career issues, while the sample consisted of 305 manually labeled comments categorized as Workload, Work Environment, and Work Compensation. Data were processed through cleansing, case folding, normalization, tokenization, stopword removal, and stemming, followed by TF-IDF feature extraction. An SVM model with a linear kernel and C = 1.0 was trained using an 80:20 data split and evaluated using a confusion matrix, accuracy, precision, recall, and F1-score. The results showed an accuracy of 96.72% and macro precision, recall, and F1-score of 96.67%. The model correctly classified 59 of 61 testing comments. In conclusion, the NLP-TF-IDF-SVM approach effectively classified career concern topics and was successfully implemented in a functional web-based classification system.

References

Abdurrazik, & Wirawana, I. M. W. (2025). Analisis klasifikasi tweet berdasarkan topik sosial menggunakan SVM. JNATIA, 3(4).
Agustian, A. A., & Bisri, A. (2019). Data mining optimization using sample bootstrapping and particle swarm optimization in the credit approval classification. Indonesian Journal of Artificial Intelligence and Data Mining, 2(1), 18–27. https://doi.org/10.24014/ijaidm.v2i1.6299
Bahram, M. (2023). Transformasi masyarakat di era digital: Menjaga kaidah hukum sebagai landasan utama. 2(5), 1733–1746.
Fide, S., Suparti, & Sudarno. (2021). Analisis sentimen ulasan aplikasi TikTok di Google Play menggunakan metode Support Vector Machine (SVM) dan asosiasi. Jurnal Gaussian, 10(3), 346–358. https://ejournal3.undip.ac.id/index.php/gaussian/
Herlinda, V. A., Aditya, C. S. K., & Chandranegara, D. R. (2024). Analisis sentimen masyarakat terhadap Generasi Z dalam dunia kerja pada media sosial Twitter menggunakan metode Naïve Bayes. REPOSITOR, 6(4), 405–414.
Hilmi, N. F., & Irwiensyah, F. (2024). Analisis sentimen terhadap aplikasi TikTok dari ulasan pada Google Playstore menggunakan metode Naïve Bayes. Smatika Jurnal, 14(1), 146–156. https://doi.org/10.32664/smatika.v14i01.1210
Indrayuni, E., Nurhadi, A., & Kristiyanti, D. A. (2021). Implementasi algoritma Naive Bayes, Support Vector Machine, dan K-Nearest Neighbors untuk analisa sentimen aplikasi Halodoc. Faktor Exacta, 14(2), 64. https://doi.org/10.30998/faktorexacta.v14i2.9697
Indriyani, F. A., Ahmad, F., & Sutan, F. (2023). Analisis sentimen aplikasi TikTok menggunakan algoritma Naïve Bayes dan Support Vector Machine. TEKNOSAINS: Jurnal Sains, Teknologi dan Informatika, 10(2), 176–184. https://doi.org/10.37373/tekno.v10i2.419
Kurniawan, E. P., S, I. B. H., & Irwansyah. (2021). Pengungkapan diri di situs media sosial YouTube. Jurnal Lensa Mutiara Komunikasi, 5(1), 42–51. https://doi.org/10.51544/jlmk.v5i1.1526
Luwei, W., & Huimin, M. (2024). From jobs to careers: Drivers and barriers to career development in emerging labor markets. Frontiers in Sociology, 9, Article 1486871. https://doi.org/10.3389/fsoc.2024.1486871
Mardianto, D. (2023). Komunikasi ekspresif penggunaan media sosial TikTok (Studi kasus Generasi Z usia 18–23 tahun). IKOMIK: Jurnal Ilmu Komunikasi dan Informasi, 3(2), 50–58. https://doi.org/10.33830/ikomik.v3i2.6481
Mutawalli, L., Zaen, M. T. A., & Bagye, W. (2019). Klasifikasi teks sosial media Twitter menggunakan Support Vector Machine (Studi kasus penusukan Wiranto). Jurnal Informatika dan Rekayasa Elektronik, 2(2), 43. https://doi.org/10.36595/jire.v2i2.117
Putra, T. I. Z. M., Suprapto, & Bukhori, A. F. (2022). Model klasifikasi berbasis multiclass classification dengan kombinasi IndoBERT embedding dan Long Short-Term Memory untuk tweet berbahasa Indonesia. Jurnal Ilmu Siber dan Teknologi Digital, 1(1), 1–28. https://doi.org/10.35912/jisted.v1i1.1509
Rifaldi, D., Fadlil, A., & Herman. (2023). Teknik preprocessing pada text mining menggunakan data tweet “mental health.” DECODE: Jurnal Pendidikan Teknologi Informasi, 3(2), 161–171.
Wibowo, I. S., Witanti, A., & Susilawati, I. (2024). Keyword extraction judul berita online di Indonesia menggunakan metode TF-IDF. Jurnal Teknik Informatika dan Sistem Informasi, 11(1), 99–111.
Wicaksana, D. G. A., & Rudy, D. G. (2021). Perlindungan konsumen “curhat online” dalam platform media sosial. Jurnal Magister Hukum Udayana (Udayana Master Law Journal), 10(3), 644. https://doi.org/10.24843/jmhu.2021.v10.i03.p15