A Data-Driven Intelligent Optimization Framework for Automated Text Classification

Abstract

This paper proposes an intelligent optimization framework for text classification based on data-driven machine learning models. To address the limitations of traditional parameter tuning in classification algorithms, a swarm intelligence-inspired optimization approach is employed to enhance model convergence and generalization. The framework integrates word vector representation, feature weighting, and adaptive optimization mechanisms to improve semantic understanding and classification precision. A large-scale Chinese text dataset is used to evaluate the performance of the model through metrics including precision, recall, and F1-score. Experimental results demonstrate that the proposed approach effectively improves parameter search efficiency, enhances classification accuracy across multiple categories, and achieves superior performance compared with conventional optimization and learning methods. The study provides a scalable methodology for intelligent text analysis and contributes to the broader application of data-driven optimization in natural language processing and automated information systems.