arrow
返回

Variable Convolution and Pooling Convolutional Neural Network for Text Sentiment Classification

delete2020-01-01
delete26
delete
OA
AI
M
Min Dong
Y
Yongfa Li
X
Xue Tang
J
Jingyun Xu
S
Sheng Bi *
蔡毅 封面图
蔡毅 (Yi Cai) *
DOI:10.1109/ACCESS.2020.2966726delete
delete原文链接
delete分享
delete收藏
查看原文
摘要

摘要

En 中文
With the popularity of the internet, the expression of emotions and methods of communication are becoming increasingly abundant, and most of these emotions are transmitted in text form. Text sentiment classification research mainly includes three methods based on sentiment dictionaries, machine learning and deep learning. In recent years, many deep learning-based works have used TextCNN (text convolution neural network) to extract text semantic information for text sentiment analysis. However, TextCNN only considers the length of the sentence when extracting semantic information. It ignores the semantic features between word vectors and only considers the maximum feature value of the feature image in the pooling layer without considering other information. Therefore, in this paper, we propose a convolutional neural network based on multiple convolutions and pooling for text sentiment classification (variable convolution and pooling convolution neural network, VCPCNN). There are three contributions in this paper. First, a multiconvolution and pooling neural network is proposed for the TextCNN network structure. Second, four convolution operations are introduced in the word embedding dimension or direction, which are helpful for mining the local features on the semantic dimensions of word vectors. Finally, average pooling is introduced in the pooling layer, which is beneficial for saving the important feature information of the extracted features. The verification test was carried out on four emotional datasets, including English emotional polarity, Chinese emotional polarity, Chinese subjective and objective emotion and Chinese multicategory. Our apporach is effective in that its result was up to 1.97% higher than that of the TextCNN network.
Keyword:
Text sentiment classification
deep learning
CNN
AI总结

AI总结

对已上传原文的论文进行重点信息的提取,主要内容包括:简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。

期刊

IEEE Access 封面图
IEEE Access
IF:
3.6
论文数:
9.8W
被引数:
36.3W

机构

华南理工大学 封面图
华南理工大学
学者数:
6.0K
论文数: 2.0K
被引数: 4.4W
引用论文

引用论文

err分享
err收藏
Risk of Thrombosis in Adult Philadelphia-Positive ALL Treated with an Asparaginase-Free Pediatric-Inspired ALL Regimen with Imatinib
err2019-11-13
err0
errOAAI
errRuiqi Chen; Xing Liu; Solaf Kanfar; Dawn Maze; Steven M Chan; Vikas Gupta; Karen W.L. Yee; Mark D. Minden; Aaron D Schimmer; Andre C. Schuh; Caroline J McNamara; Tracy Murphy; Anna Xu; Umberto Falcone; Jack Seki; Hassan Sibai
err分享
err收藏
err分享
err收藏
An improved algorithm for sentiment analysis based on maximum entropy
err2017-11-01
err45
PREAI
errXie, Xin; Ge, Songlin; Hu, Fengping; Xie, Mingye; Jiang, Nan
err分享
err收藏
Sentiment Analysis of Big Data: Methods, Applications, and Open Challenges
err2018-01-01
err89
errOAAI
errShayaa, Shahid; Jaafar, Noor Ismawati; Bahri, Shamshul; Sulaiman, Ainin; Wai, Phoong Seuk; Chung, Yeong Wai; Piprani, Arsalan Zahid; Al-Garadi, Mohammed Ali
err分享
err收藏
学者 查看更多内容