<![CDATA[Gender-based violence remains a critical social issue in Indonesia, generating substantial public discourse across digital platforms. This study applies Latent Dirichlet Allocation (LDA)-based topic modeling to identify and compare the dominant themes emerging in online discussions of gender-based violence across three platforms: X (formerly Twitter), YouTube, and the news portal Detik.com. A total of 21,000 data points were collected through keyword-based web scraping covering the period January 2020 to October 2025. The two-phase modeling process yielded coherence scores of 0.38 and 0.53 for X, 0.77 and 0.73 for YouTube, and 0.8 and 0.52 for Detik.com across the first and second phases, respectively, reflecting differences in language register and content structure across platforms. A two-phase modeling approach was employed for each platform to progressively refine topic quality and eliminate irrelevant outputs. The results show that LDA successfully identified platform-specific thematic patterns: X captured emotional and psychological dimensions of gender-based violence, YouTube surfaced legislative and advocacy-oriented discourse centered on the PKS Law, and Detik.com produced case-specific topics grounded in legal proceedings and journalistic reporting. Across all three platforms, domestic violence emerged as the most consistently prominent theme. These findings demonstrate that a multi-platform approach yields a more comprehensive and nuanced picture of public discourse on gender-based violence than any single-source analysis, and that LDA is an effective tool for large-scale thematic extraction from heterogeneous online text data.]]>
