PREDICTING PUBLIC TRANSPORTATION CROWD USING WEATHER API AND SOCIAL MEDIA

The rapid growth of urban populations and the increasing reliance on public transportation services such as buses, trains, and metro systems have made effective crowd management a major challenge in modern cities. Overcrowding not only affects passenger safety and comfort but also impacts operational efficiency and infrastructure sustainability. This research proposes a hybrid machine learning framework for real-time crowd prediction in public transportation systems using multi-source data analytics. The system integrates environmental data from Weather APIs, traffic congestion indicators, social media activity signals, peak-hour trends, and geospatial information to better understand urban mobility patterns. A Random Forest classifier is used as the primary prediction model due to its robustness and ability to handle heterogeneous datasets. The framework is implemented as a full-stack web application using React.js, Node.js, Express.js, and MongoDB. The model classifies crowd density into Low, Medium, and High levels. Experimental results demonstrate improved scalability, predictive performance, and responsiveness, supporting smart city transportation planning and proactive crowd management.