基因遗传算法在文本情感分类中的应用

本文以微博文本为主要实验对象,提出适合卷积神经网络进行自我优化的编码方式,分别将每一层看做是一个染色体,将每一层中的参数看做是一个基因片段,采用混合双重非数值编码的方式编码每个CNN框架,设计出适合于CNN网络的选择、交叉和变异的算法,并且把基因遗传算法(GA)和与卷积神经网络相结合,提出了基于情感分析算法的遗传算法(GA-CNN).通过对传统算法与GA-CNN的实验与对比分析,良好地展示了自我优化性.

Application of genetic algorithm in text sentiment classification

In this paper, we use Sina Weibo text as the main experimental dataset, and propose a coding method suitable for self optimization of convolutional neural networks. Our coding method encodes each CNN framework using a hybrid double non numeric encoding by treating each layer as a chromosome and the parameters in each layer as a gene segment respectively, and selection, crossover and mutation algorithms are devised for CNN networks. We also propose a genetic algorithm based on sentiment analysis algorithm (GA CNN) which combines genetic algorithm (GA) with convolutional neural network. The experiment and comparative analysis of GA CNN and traditional algorithms demonstrates the self optimization of our method.