Urban opinion from crowdsourced data often leads to imbalanced datasets due to the diversity of issues related to urban social, economic, and environmental topics. This study presents a novel hybrid approach that combines Random Over-Sampling and Random Forest (ROS-RF) to effectively classify such imbalanced data. Using crowdsourced urban opinion data from Jakarta, experimental results show that the ROS-RF method outperforms other approaches. The ROS-RF classifier achieved an impressive F1-score, recall, precision, and accuracy of 98%. These findings highlight the superior effectiveness of the ROS-RF method in classifying urban opinions, especially those related to social, economic, and environmental issues in urban settings. This hybrid approach provides a robust solution for managing imbalanced datasets, ensuring more accurate and reliable classification outcomes. The study underscores the potential of ROS-RF in enhancing urban data analysis and decision-making processes