针对传统朴素贝叶斯分类模型应用过程中存在的特征项冗余问题,使用遗传禁忌算法对特征项集进行优化,并在此优化结果的基础上,提出了一种改进的朴素贝叶斯分类方法来解决用户模板中存在的单类别词汇问题。经实验证明,该方法比传统的朴素贝叶斯分类模型具有更好的鲁棒性和分类性能。
For the feature redundancy issues of traditional naive Bayesian classification,this paper introduced genetic tabu algorithm to optimize the set of feature,proposed an improved naive Bayesian model solving single-category vocabulary based on this optimization results. The experiments show that this method has better robustness and classification performance.