基于遗传支持向量机算法的文本分类

Text Classification Based on Genetic Algorithm and Support Vector Machine

支持向量机具有良好的泛化和高维模式识别能力,广泛地应用于文本分类中。然而,文本分类的准确性却很大程度上依赖于参数惩罚因子(C)和核函数(γ)的正确选择。运用遗传算法优化支持向量机参数,选取文本分类准确率作为适应度函数,通过种群进化实现支持向量机参数寻优,构造基于遗传向量机算法的文本分类器(GA-SVM)。实验表明,改进后的文本分类器(GA-SVM)在准确度和运行速度都有明显的提高,具有较强的可行性和实用性。

Support vector machine has a high dimensional pattem recognition capability, so it is widely used in text classification. However, the accuracy of text classification is highly depended on the right selection of penalty factor and kernel function parameter. This paper adopts genetic algorithm to optimize the parameters of support vector rmchine, and selects text classification accuracy as fitness function. Based on genetic algorithm and support vector machine, a text classitier （GA-SVM） is constructed through the evolution to opt~ support vector rmchine parameters. Experiments show that the accuracy and operation speed for improved classifier （GA-SVM） has irnproved significantly.