Probabilistic Clustering for Hyperspherical Data: Extending the Boosted-Oriented Approach with a Textual Data Application

Clustering techniques have gained significant attention in the literature over the years and have been adapted to various types of data. In this work, we propose an innovative approach for clustering hyperspherical data by extending the boosted-oriented probabilistic clustering algorithm to this specific context. We also implement this methodology on a textual data set to group documents based on the words they contain.