<![CDATA[Introduction: Cross-platform sentiment analysis for Indonesian language presents significant challenges when adapting models from general applications to specialized domains. Domain Adversarial Neural Networks (DANN) offer promising solutions for transfer learning, yet their effectiveness for Indonesian language remains largely unexplored, particularly under extreme class imbalance conditions common in trading platforms. Methods: This study investigates DANN effectiveness for transferring sentiment analysis knowledge from four strategically selected source domains to TradingView trading platform. The research utilizes 5,990 Indonesian reviews after preprocessing from an initial 6,000 samples, with source domains showing 66.5% positive sentiment while target domain exhibits 85.1% positive sentiment, creating an 18.7% distribution gap. Four experimental approaches were compared with statistical validation across multiple random initializations: Source-Only training, Multi-Domain training, Limited Target training, and DANN implementation. Results: DANN demonstrates stable cross-platform adaptation, achieving 87.77% ± 0.97% accuracy with consistent performance across initializations, outperforming Source-Only baseline (87.10% ± 0.84%) and Multi-Domain approach (86.98% ± 0.64%). While Limited Target baseline achieves higher accuracy (88.10% ± 2.23%), its high variance poses deployment risks. A-distance analysis reveals substantial domain gaps (193.00 ± 1.06), with DANN's adversarial training achieving modest domain separation reduction (72.90% ± 8.81% domain discrimination accuracy). Conclusions: This research contributes the first systematic evaluation of DANN for Indonesian cross-platform sentiment analysis, demonstrating that deployment consistency outweighs peak accuracy for production environments. The findings provide practical value for Indonesian fintech startups requiring robust sentiment analysis with limited labeled data. Future work should explore multi-target adaptation and optimization strategies for diverse Indonesian business domains]]>
