首页 | 本学科首页   官方微博 | 高级检索  
检索        

基于深度LSTM神经网络的在线消费评论情感分类研究
引用本文:周 虎,于 跃,贾媛媛,赵文龙.基于深度LSTM神经网络的在线消费评论情感分类研究[J].中华医学图书情报杂志,2018,27(5):23-29.
作者姓名:周 虎  于 跃  贾媛媛  赵文龙
作者单位:重庆医科大学医学信息学院,重庆 400016,重庆医科大学医学信息学院,重庆 400016,重庆医科大学医学信息学院,重庆 400016,重庆医科大学医学信息学院,重庆 400016
基金项目:国家自然科学基金“基于深度卷积生成对抗网络的3D-MRI图像超分辨率重建研究”(61702064)和中国博士后科学基金“基于稀疏表示的4D-MRI图像超分辨率重建研究”(2017M623303XB)的研究成果之一
摘    要:目的:探索深度神经网络在情感分类方面的应用。方法:采用长短型记忆神经网络构造在线消费评论情感的分类器,对收集的消费评论进行二分类的情感分析。结果:LSTM模型的准确率为89.29%,优于实验对照SVM模型的86.10%,深度神经网络模型在本文的情感分类中的准确率较高。结论:使用深度神经网络对消费评论的情感进行分类,可减少人工特征的干预,提高在线消费评论情感分类的效率。

关 键 词:在线评论  情感分析  神经网络  支持向量机  深度学习
收稿时间:2018/1/12 0:00:00

Deep long-short term memory neural network-based sentiment classification of online reviews on consumption
ZHOU Hu,YU Yue,JIA Yuan-yuan and ZHAO Wen-long.Deep long-short term memory neural network-based sentiment classification of online reviews on consumption[J].Chinese Journal of Medical Library and Information Science,2018,27(5):23-29.
Authors:ZHOU Hu  YU Yue  JIA Yuan-yuan and ZHAO Wen-long
Institution:School of Medical Informatics of Chong Qing Medical University, Chongqing 400016, China,School of Medical Informatics of Chong Qing Medical University, Chongqing 400016, China,School of Medical Informatics of Chong Qing Medical University, Chongqing 400016, China and School of Medical Informatics of Chong Qing Medical University, Chongqing 400016, China
Abstract:Objective To study the application of deep long-short term memory (LSTM) neural network in sentiment classification.Methods A sentiment classifier for online reviews on consumption was made using the LSTM neural network. The binary catalogued sentiment of recorded online reviews on consumption was analyzed. Results The accuracy of LSTM model was higher than that of SVM model for sentiment classification (89.29% vs 86.10%). A rather high accuracy of deep neural network was achieved for sentiment classification in this study. Conclusion Deep neural network-based sentiment classification of online reviews on consumption can reduce the intervention of artificial features and improve the sentiment classification efficacy of online reviews on consumption.
Keywords:Online review  Sentiment analysis  Neural network  Vector-supporting machine  Deep learning
点击此处可从《中华医学图书情报杂志》浏览原始摘要信息
点击此处可从《中华医学图书情报杂志》下载免费的PDF全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号