Abstract

The rapid growth of smart devices and the Internet of Things (IoT) has significantly increased data generation, enabling deeper insights into human behavior through intelligent Big Data analytics. Traditional data processing methods struggle to handle the complexity and volume of such data, necessitating more efficient and scalable solutions. This research focuses on leveraging advanced technologies such as Hadoop, Spark, and Hive to analyze human behavioral patterns in the Social Internet of Things (SIoT). The proposed system architecture integrates real-time data processing to extract valuable insights from social media interactions, wearable sensors, and smart city infrastructures. By applying machine learning algorithms and data mining techniques, the system enhances behavioral predictions, improves decision-making processes, and enables intelligent automation. The study also compares the efficiency of Spark-based processing with conventional single-threaded approaches, demonstrating significant improvements in execution time and analytical accuracy. The experimental results validate the effectiveness of the proposed framework in analyzing complex human dynamics, offering applications in various domains such as urban development, healthcare, security, and personalized recommendations. This research highlights the potential of Big Data-driven analytics in transforming human behavior analysis and fostering smarter, data-driven ecosystems.