Clustering Analysis of College English Translation Based on Multi-Strategy Artificial Bee Colony Algorithm

To enhance the accuracy of clustering analysis for college English translation texts and to overcome the issues of traditional methods such as susceptibility to local optima and poor adaptability to high-dimensional sparse data, this study employs a Multi-Strategy Artificial Bee Colony (MS-ABC) algorithm. Taking college students’ English translation texts as the research object, it investigates their clustering characteristics and patterns. Specifically, the proposed MS- ABC algorithm integrates chaotic map initialization, adaptive neighborhood search, dynamic selection strategy, elite preservation mechanism, and simulated annealing concepts. A translation clustering model is established covering feature representation, objective function, and optimization of clustering centers. Experimental results demonstrate that, compared to the conventional ABC algorithm and K-means, the proposed model achieves superior performance on clustering evaluation indicators such as the F1-score and Silhouette coefficient. This indicates its effectiveness in handling high dimensionality, sparsity, and semantic complexity inherent in translated texts. Findings of this research can provide technical support for intelligent classification of educational resources.