基于双向LSTM模型的文本情感分类  

Sentiment analysis of text based on bi-directional long short-term memory model

作　　者：任勉 甘刚 REN Mian,GAN Gang(College of Cybersecurity,Chengdu University of Information Technology,Chengdu 610225,Chin)

机构地区：[1]成都信息工程大学网络空间安全学院,四川成都610225

出　　处：《计算机工程与设计》2018年第7期2064-2068,共5页Computer Engineering and Design

基　　金：国家重大科技专项基金项目(2014ZX01032401-001)

摘　　要：为解决文本情感分类研究中传统循环神经网络模型存在梯度消失和爆炸问题,提出一种基于双向长短时记忆循环神经网络模型(Bi-LSTM)。通过双向传播机制获取文本中完整的上下文信息,采用CBOW模型训练词向量,减小词向量间的稀疏度,结合栈式自编码深度神经网络作为分类器。实验结果表明,Bi-LSTM模型比传统循环神经网络LSTM模型分类效果更好,对比实验中Bi-LSTM2能达到更优的召回率和准确率。To solve the problems of gradient disappearance and explosion in the traditional cyclic neural network model of text sentiment analysis,a neural network model based on bi-directional long short-term memory（Bi-LSTM）loop was proposed.The bi-directional mechanism was used to obtain the complete context information in the text,and the continuous bag of words model was used to train the word vector to reduce the sparseness between the word vectors,and the stack self-coding depth neural network was used as the classifier.Experimental results show that the Bi-LSTM model is better than the traditional cyclic neural network LSTM model,and the Bi-LSTM2 can achieve better recall rate and accuracy.

关 键 词：双向长短时记忆循环神经网络 词向量 长短时记忆网络 循环神经网络 文本情感倾向性分析 

分 类 号：TP391.1[自动化与计算机技术—计算机应用技术]