Developing efficient automatic classification and discovery methods is necessary due to the increasing number of online web services. This study analyses and compares several clustering algorithms and feature extraction techniques to enhance the organizational structure and retrieval of web services. Specifically, it investigates textual, structural, and semantic feature extraction techniques, which are subsequently combined with clustering algorithms such as K-Means, Hierarchical Clustering, and Density-Based Spatial Clustering of Applications with Noise (DBSCAN). The study aims to evaluate the performance of these combinations in terms of classification accuracy, computational efficiency, and the quality of the resulting service categories. Experiments are conducted using benchmark datasets that reflect diverse real-world scenarios. The results indicate that different integrations of feature extraction and clustering methods provide varying levels of effectiveness, depending on the context and data characteristics. By analyzing these outcomes, the study offers practical guidance for selecting suitable Algorithms to support automated web service classification, improving service discovery processes, and enhancing service-oriented architectures’ overall usability and scalability.