Enhanced Framework for Multi-Label Text Classification Using Beta Ant Colony Optimisation (BACO) Ensembling Approach

One of the most significant issues associated with enormous amounts of data is effectively categorizing text that has a high number of categories. This is especially true in healthcare and online buying and selling. The Beta Ant Colony Optimization (BACO) technique is proposed in this research within a multi-label text categorization system. This research makes use of an ensemble technique to enhance the accuracy of feature selection and classification. BACO is able to change pheromone updates to minimize dimensionality in an effective manner while simultaneously increasing label assignment. This is accomplished via the use of beta distributions and the collective intelligence of ant colonies. On a large number of high-dimensional datasets, BACO is tested in comparison to the most advanced approaches currently available. By enhancing the categorization of text with multiple labels, the results suggest that BACO may be able to enhance classification in complicated settings.