基于BiGRU-CNN的中文评论文本情感分析
首发时间:2019-04-26
摘要:近年来,互联网上中文评论文本的激增使得使用深度学习方法进行评论文本情感分析成为一种趋势。目前常用的深度学习模型是基于卷积神经网络(CNN)和循环神经网络(RNN),而RNN中包括长短期记忆网络(LSTM)和门控循环单元(GRU)两种变体模型。为了提高评论文本情感分析的acc(准确率),本文将RNN和CNN进行结合,提出一种融合双向门控循环单元(BiGRU)和CNN的BiGRU-CNN文本情感分析模型,该模型在评论文本数据集上的acc达到了93.27%,相比基本的模型提高了文本情感分析的acc,并且模型训练时间适中。
关键词: 情感分析 深度学习 循环神经网络 门控循环单元 卷积神经网络
For information in English, please click here
Sentiment Analysis of Chinese Comment Text Based on BiGRU-CNN
Abstract:In recent years, the explosion of Chinese comment texts on the Internet has made it a trend to use in-depth learning methods for sentiment analysis of comment texts. At present, the commonly used deep learning model is based on convolutional neural network (CNN) and recurrent neural network (RNN), and RNN includes two structures: long-short term memory (LSTM) and gated recurrent unit (GRU). In order to improve the accuracy of sentiment analysis of comment text, this paper combines RNN with CNN, and proposes a BiGRU-CNN text sentiment analysis model which integrates BiGRU and CNN. The accuracy of this model on comment text dataset reaches 93.27%. Compared with the basic CNN, LSTM and GRU models, this model improves the accuracy of sentiment analysis of text and the training time of the model is moderate.
Keywords: sentiment analysis deep learning recurrent neural network gated recurrent unit convolutional neural network
基金:
引用
No.****
动态公开评议
共计0人参与
勘误表
基于BiGRU-CNN的中文评论文本情感分析
评论
全部评论0/1000