Klasifikasi Konten AI-Generated dan Non-AI pada Teks Hashtag dan Komentar TikTok Menggunakan Logistic Regression

Main Article Content

Khalifah Safa Rizky Khalifah
Irwansyah
Tupan Tri M

Abstract

The widespread distribution of AI-generated content on TikTok raises concerns about disinformation and the authenticity of online interaction. Most previous studies emphasise visual features, whereas textual features such as hashtags and user comments remain underexplored. This study aims to classify AI-generated and non-AI content on TikTok using the text of hashtags and user comments with the Logistic Regression method. Data were collected through web scraping with Apify and, after cleaning, 1,008 text records were obtained. Preprocessing consisted of case folding, removal of URLs, mentions, hashtags and non-alphabetic characters, tokenisation, stop-word filtering and stemming. The text was converted into numerical features using Term Frequency–Inverse Document Frequency (TF-IDF), and the data were split 70:30 into 705 training and 303 testing records. The model was built and evaluated in RapidMiner Studio using a confusion matrix. It achieved an overall accuracy of 72.28%. For the non-AI class, precision, recall and F1-score were 74.45%, 86.67% and 80.09%, whereas for the AI-generated class they were 65.79%, 46.30% and 54.35%. The low recall of the AI-generated class was caused by 58 false negatives. These findings indicate that Logistic Regression with TF-IDF can serve as a lightweight baseline for text-based detection of AI-generated content on TikTok, but class imbalance and the ambiguity of short, informal text still limit its sensitivity.

Article Details

Section

Articles

How to Cite

Klasifikasi Konten AI-Generated dan Non-AI pada Teks Hashtag dan Komentar TikTok Menggunakan Logistic Regression. (2026). DIGINTEL-AI : DIGital INnovation and InTELligence – AI, 2(1), 1-10. https://doi.org/10.66217/digintel-ai.v2i1.21

References

Abidin, M. I., Nurtanio, I., & Achmad, A. (2022). Deepfake detection in videos using long short-term memory and CNN ResNext. Jurnal Ilmiah ILKOM, 14(3), 178–185. https://doi.org/10.33096/ilkom.v14i3.1254.178-185

Agistina, S. D., Irwansyah, I., Budiyantara, A., & Irwiensyah, F. (2026). Klasifikasi metode Naïve Bayes pada ulasan pengguna aplikasi Dazzcam untuk pengeditan foto vintage di App Store. DIGINTEL-AI: DIGital INnovation and inTELligence – AI, 1(2). https://doi.org/10.66217/digintel-ai.v1i2.9

Alexander, S. G., Ananto, A. T., Adhitya, I. P., Mangku, P., & Liano, B. (2023). Analisis sentimen opini masyarakat Indonesia terhadap konten deepfake tokoh publik. KAKIFIKOM (Kumpulan Artikel Karya Ilmiah Fakultas Ilmu Komputer), 5(2), 95–102. https://doi.org/10.54367/kakifikom.v5i2.3496

Alonso-López, N., Sidorenko-Bautista, P., & Giacomelli, F. (2021). Beyond challenges and viral dance moves: TikTok as a vehicle for disinformation and fact-checking in Spain, Portugal, Brazil, and USA. Anàlisi: Quaderns de Comunicació i Cultura, 64, 65–84. https://doi.org/10.5565/rev/analisi.3411

April, V. N., Manalu, P. D., Simanjuntak, M., & Umri, C. (2025). Implementasi algoritma klasifikasi untuk analisis sentimen media sosial TikTok tahun 2025. JUTITI, 5(2). https://doi.org/10.55606/jutiti.v5i2.5644

Cahyani, O. N., et al. (2025). Performa logistic regression dan naive Bayes dalam klasifikasi berita hoax di Indonesia. Edumatic: Jurnal Pendidikan Informatika, 9(1), 60–68. https://doi.org/10.29408/edumatic.v9i1.28987

Daulay, S. H., Saragih, A. S., & Bidadari, L. (2025). Linguistic strategies in the dissemination of hoaxes on TikTok: The role of hashtags in shaping public … Journal of Applied Linguistic and Studies of Cultural, 2(2), 9–19. https://doi.org/10.65787/jalc.v3i2.556

Devlin, J., Chang, M. W., Lee, K., & Toutanova, K. (2019). BERT: Pre-training of deep bidirectional transformers for language understanding. Proceedings of NAACL-HLT. https://doi.org/10.48550/arXiv.1810.04805

Fadhilah, R. R. N. (2023). Dampak penyalahgunaan deepfake dalam memanipulasi informasi. Jurnal Kawistara. https://doi.org/10.22146/kawistara.98339

Fany, K. D., Irwansyah, I., Shidqon, M., & Pratiwi, N. (2026). Perbandingan kinerja algoritma K-Nearest Neighbor dan Decision Tree dalam analisis sentimen ulasan aplikasi DANA pada Google Play Store. DIGINTEL-AI: DIGital INnovation and inTELligence – AI, 1(2). https://doi.org/10.66217/digintel-ai.v1i2.11

Guo, B., Zhang, X., Wang, Z., Jiang, M., Nie, J., Ding, Y., Yue, J., & Wu, Y. (2023). How close is ChatGPT to human experts? Comparison corpus, evaluation, and detection. arXiv. https://doi.org/10.48550/arXiv.2301.07597

Mitchell, E., Lee, Y., Khazatsky, A., Manning, C. D., & Finn, C. (2023). DetectGPT: Zero-shot machine-generated text detection using probability curvature. Proceedings of the 40th International Conference on Machine Learning, 202, 24950–24962. https://doi.org/10.48550/arXiv.2301.11305

Nida, A. S., Irwansyah, I., Wiranata, A. D., & Halim, Z. (2026). Perbandingan Naive Bayes Classifier dan SVM untuk analisis sentimen desain seragam atlet Indonesia pada media sosial X di Olimpiade Paris 2024. DIGINTEL-AI: DIGital INnovation and inTELligence – AI, 1(2). https://doi.org/10.66217/digintel-ai.v1i2.13

Nirmala, N. M. G. S., & Sanjaya E. R., N. A. (2024). Analisis sentimen dengan logistic regression untuk deteksi kata pada Livin’ by Mandiri. Jurnal Nasional Teknologi Informasi dan Aplikasinya, 2(4), 869–878. https://doi.org/10.24843/JNATIA.2024.v02.i04.p25

Putri, A. N., Prasetyo, R. A., & Crisnawati, C. I. G. (2026). Analisis sentimen terhadap AI dalam pendidikan di media sosial menggunakan metode kuantitatif logistic regression. Jurnal Elektro dan Informatika Swadharma (JEIS), 6(1), 69–77. https://doi.org/10.56486/jeis.vol6no2.1129

Rahayu, N. A., & Sudjradjat, R. H. (2025). The influence of non-AI and AI-generated TikTok true story content on Generation Z’s perceptions (A study on elaboration likelihood theory). INJECT: Interdisciplinary Journal of Communication, 10(1), 821–846. https://doi.org/10.18326/inject.v10i1.4504

Rendra, S., et al. (2024). Optimasi model machine learning untuk analisis sentimen data komentar TikTok tentang kemajuan Ibu Kota Nusantara. Journal of Informatics and Vocational Education, 5(4), 200–215. https://doi.org/10.46336/ijmsc.v3i3.232

Rizal, F. (2024). Analisis sentimen masyarakat Indonesia terhadap aplikasi TikTok menggunakan logistic regression. Jurnal Akiratech, 2(1), 20–30. https://doi.org/10.63935/akiratech.v1i2.33

Sadasivan, V. S., Kumar, A., Balasubramanian, S., Wang, W., & Feizi, S. (2023). Can AI-generated text be reliably detected? arXiv. https://doi.org/10.48550/arXiv.2303.11156

Setyawan, A., Fitriani, A., & Rilvani, E. (2025). Klasifikasi kemiskinan di Indonesia dengan decision tree menggunakan RapidMiner. Jurnal Media Akademik (JMA), 3(7). https://doi.org/10.62281/v3i7.2646

Triyono, L., Gernowo, R., Rahaman, M., & Raharjo, T. (2023). Indonesian fake news detection using various machine learning technique. International Journal on Informatics Visualization, 7(3), 726–732. https://doi.org/10.30630/joiv.7.3.1243

Uchendu, A., Ma, Z., Le, T., Zhang, R., & Lee, D. (2021). TuringBench: A benchmark environment for Turing test in the age of neural text generation. Findings of the Association for Computational Linguistics: EMNLP 2021, 2001–2016. https://doi.org/10.18653/v1/2021.findings-emnlp.172

Wu, J., Yang, S., Zhan, R., Yuan, Y., Chao, L. S., & Wong, D. F. (2025). A survey on LLM-generated text detection: Necessity, methods, and future directions. Computational Linguistics, 51(1). https://doi.org/10.1162/coli_a_00549

Similar Articles

You may also start an advanced similarity search for this article.