In order to improve comprehension of interactions within digital contexts, the primary objective of this project is to classify internet users based on information-seeking behaviors and machine learning methodologies. It is imperative to understand user preferences, online behaviors, and search queries in order to improve cybersecurity applications, recommendation systems, targeted advertising, and personalized services, given the rapid proliferation of the internet and digital platforms. The research classifies individuals based on a variety of online behaviors, including the frequency of content interactions, browser history, search queries, and click patterns. Machine learning methodologies, such as Naïve Bayes, K-Nearest Neighbor (KNN), Support Vector Machine (SVM), Decision Tree, and Random Forest, are implemented to identify patterns and improve classification precision. The efficacy of a model is improved by data preprocessing methods, including feature extraction, normalization, and noise reduction. By analyzing their informationseeking behaviors, the proposed system can distinguish between casual browsers, goaloriented users, and information seekers. Machine learning algorithms are capable of
accurately and rapidly classifying internet users into multiple categories, as evidenced by
experiments. This research contributes to the development of intelligent web systems that
improve user experiences, facilitate the delivery of content more flexibly, and assist users in
making informed decisions on digital platforms.