Performa Multinomial Naive Bayes dalam Klasifikasi Misinformasi Megathrust pada Komentar TikTok

Febri Yalda Sulistia; Karina Nurfebia; Nurbeti Sinulingga; Nuzul Aini Ramadhani; Khairul Khairul

doi:10.60076/indotech.v4i2.2090

Authors

Febri Yalda Sulistia Universitas Pembangunan Panca Budi
Karina Nurfebia Universitas Pembangunan Panca Budi
Nurbeti Sinulingga Universitas Pembangunan Panca Budi
Nuzul Aini Ramadhani Universitas Pembangunan Panca Budi
Khairul Khairul Universitas Pembangunan Panca Budi

DOI:

https://doi.org/10.60076/indotech.v4i2.2090

Keywords:

Misinformasi Megathrust, Komentar TikTok, Multinomial Naive Bayes, TF-IDF, Misinformasi Kebencanaan

Abstract

Penyebaran misinformasi terkait bencana megathrust di media sosial TikTok berpotensi memicu kepanikan publik dan mengganggu efektivitas komunikasi risiko bencana. Penelitian ini bertujuan menganalisis model klasifikasi informasi valid dan misinformasi terkait megathrust menggunakan pendekatan Natural Language Processing (NLP), algoritma Multinomial Naive Bayes, dan TF-IDF. Data penelitian berupa 2.000 komentar TikTok berbahasa Indonesia yang dikumpulkan secara purposive sampling dari konten relevan dan dibagi ke dalam dua kelas: informasi valid dan misinformasi. Preprocessing meliputi case folding, cleaning, tokenizing, stopword removal, dan stemming menggunakan library Sastrawi. Evaluasi pada 400 data uji menghasilkan akurasi 52%, macro-precision 50,24%, macro-recall 50,20%, dan macro-F1 48,93%. Akurasi tersebut lebih rendah daripada majority-class baseline 54,5%, sehingga model belum memberikan peningkatan dibanding prediksi sederhana yang selalu memilih kelas mayoritas. Kesalahan paling banyak terjadi pada komentar valid yang diprediksi sebagai misinformasi. Hasil ini menunjukkan bahwa variasi bahasa informal dan keterbatasan TF-IDF dalam menangkap konteks masih menjadi tantangan utama pada klasifikasi komentar TikTok

Downloads

Download data is not yet available.

References

S. Hilberts, M. Govers, E. Petelos, and S. Evers, “The impact of misinformation on social media in the context of natural disasters: Narrative review,” JMIR Infodemiology, vol. 5, Art. no. e70413, 2025, doi: 10.2196/70413. DOI: https://doi.org/10.2196/70413

S. Mızrak, “Public's social media use during the Kahramanmaraş earthquakes on 6 February 2023,” International Journal of Disaster Risk Reduction, vol. 108, Art. no. 104541, 2024, doi: 10.1016/j.ijdrr.2024.104541. DOI: https://doi.org/10.1016/j.ijdrr.2024.104541

I. Dallo, O. Elroy, L. Fallou, N. Komendantova, and A. Yosipof, “Dynamics and characteristics of misinformation related to earthquake predictions on Twitter,” Scientific Reports, vol. 13, Art. no. 13391, 2023, doi: 10.1038/s41598-023-40399-9. DOI: https://doi.org/10.1038/s41598-023-40399-9

W. Zhai, H. Yu, and C. Y. Song, “Disaster misinformation and its corrections on social media: Spatiotemporal proximity, social network, and sentiment contagion,” Annals of the American Association of Geographers, vol. 114, no. 2, pp. 408–435, 2024, doi: 10.1080/24694452.2023.2271549. DOI: https://doi.org/10.1080/24694452.2023.2271549

C.-O. Truică and E.-S. Apostol, “It’s all in the embedding! Fake news detection using document embeddings,” Mathematics, vol. 11, no. 3, Art. no. 508, 2023, doi: 10.3390/math11030508. DOI: https://doi.org/10.3390/math11030508

D. Mouratidis, A. Kanavos, and K. Kermanidis, “From misinformation to insight: Machine learning strategies for fake news detection,” Information, vol. 16, no. 3, Art. no. 189, 2025, doi: 10.3390/info16030189. DOI: https://doi.org/10.3390/info16030189

S. Raza, D. Paulen-Patterson, and C. Ding, “Fake news detection: Comparative evaluation of BERT-like models and large language models with generative AI-annotated data,” Knowledge and Information Systems, vol. 67, no. 4, pp. 3267–3292, 2025, doi: 10.1007/s10115-024-02321-1. DOI: https://doi.org/10.1007/s10115-024-02321-1

N. Agustina, Adrian, and M. Hermawati, “Implementasi algoritma Naïve Bayes classifier untuk mendeteksi berita palsu pada sosial media,” Faktor Exacta, vol. 14, no. 4, pp. 206–213, 2021, doi: 10.30998/faktorexacta.v14i4.11259. DOI: https://doi.org/10.30998/faktorexacta.v14i4.11259

I. M. Karo Karo, Romia, S. Dewi, and P. M. Fadilah, “Hoax detection on Indonesian tweets using Naïve Bayes classifier with TF-IDF,” Journal of Information System Research, vol. 4, no. 3, pp. 914–919, 2023, doi: 10.47065/josh.v4i3.3317. DOI: https://doi.org/10.47065/josh.v4i3.3317

D. B. C. Prasetiyo, P. N. Andono, and C. Supriyanto, “Metode Naive Bayes classifier dan forward selection untuk deteksi berita hoaks bahasa Indonesia,” Jurnal Media Informatika Budidarma, vol. 7, no. 3, pp. 1541–1550, 2023, doi: 10.30865/mib.v7i3.6459. DOI: https://doi.org/10.30865/mib.v7i3.6459

S. Fernando, A. Voutama, and A. A. Hendriadi, “Klasifikasi berita hoaks kampanye pemilihan umum (Pemilu) 2024 menggunakan algoritma Naïve Bayes,” JATI (Jurnal Mahasiswa Teknik Informatika), vol. 8, no. 2, pp. 2112–2115, 2024, doi: 10.36040/jati.v8i2.9400. DOI: https://doi.org/10.36040/jati.v8i2.9400

R. Adrian, Musaddam, M. Ikhsan, and M. R. Pahlevi B., “Detection of hoax news using TF-IDF vectorizer and Multinomial Naïve Bayes and Passive Aggressive,” Media Journal of General Computer Science, vol. 1, no. 2, pp. 54–61, 2024, doi: 10.62205/mjgcs.v1i2.24. DOI: https://doi.org/10.62205/mjgcs.v1i2.24

L. Geni, E. Yulianti, and D. I. Sensuse, “Sentiment analysis of tweets before the 2024 elections in Indonesia using IndoBERT language models,” Jurnal Ilmiah Teknik Elektro Komputer dan Informatika, vol. 9, no. 3, pp. 746–757, 2023, doi: 10.26555/jiteki.v9i3.26490. DOI: https://doi.org/10.26555/jiteki.v9i3.26490

M. Y. Ridho and E. Yulianti, “From text to truth: Leveraging IndoBERT and machine learning models for hoax detection in Indonesian news,” Jurnal Ilmiah Teknik Elektro Komputer dan Informatika, vol. 10, no. 3, pp. 544–555, 2024, doi: 10.26555/jiteki.v10i3.29450. DOI: https://doi.org/10.26555/jiteki.v10i3.29450

A. Kunaefi, Z. Abidin, and R. Kusumawati, “Klasifikasi berita hoaks bahasa Indonesia menggunakan IndoBERT fine-tuning dengan pendekatan focal loss pada data tidak seimbang,” JIPI (Jurnal Ilmiah Penelitian dan Pembelajaran Informatika), vol. 10, no. 2, pp. 1706–1714, 2025, doi: 10.29100/jipi.v10i2.7811. DOI: https://doi.org/10.29100/jipi.v10i2.7811