KLASIFIKASI EMOSI KOMENTAR PENGGUNA TIKTOK TERHADAP KONTEN KESEHATAN MENTAL REMAJA MENGGUNAKAN METODE LDA DAN SVM : CLASSIFICATION OF EMOTIONS IN TIKTOK USER COMMENTS ON ADOLESCENT MENTAL HEALTH CONTENT USING LATENT DIRICHLET ALLOCATION AND SUPPORT VECTOR MACHINE METHODS

Luftia Rahma Nasution (Universitas Islam Negeri Sumatera Utara)
Sriani (State Islamic University of North Sumatra)

RABIT: Jurnal Teknologi dan Sistem Informasi Univrab
Vol 11 No 2 (2026): Juli

TikTok has become a widely used social media platform for discussing adolescent mental health issues through user comments. These comments contain valuable information related to discussion topics and emotional expressions, yet the large volume of data makes manual analysis inefficient. This study analyzed 2,153 TikTok comments to identify dominant topics and classify user emotions. The research process involved text preprocessing, Term Frequency–Inverse Document Frequency (TF-IDF) weighting, topic modeling using Latent Dirichlet Allocation (LDA), and emotion classification using Support Vector Machine (SVM). The results showed that the LDA model successfully identified several dominant topics, including bullying, family pressure, friendship issues, and economic problems. Furthermore, the SVM model classified emotions into joy, sadness, and anger categories with an accuracy of 97%, precision of 97%, recall of 97%, and F1-score of 96%. These findings indicate that the combination of LDA and SVM proved to be effective for identifying discussion topics and classifying emotions in TikTok comments related to adolescent mental health.