|Table of Contents|

An Emotion Feature Extraction Method of BiLSTM-CNN based on Orthogonal Projection(PDF)

《南京师大学报(自然科学版)》[ISSN:1001-4616/CN:32-1239/N]

Issue:
2023年01期
Page:
139-148
Research Field:
计算机科学与技术
Publishing date:

Info

Title:
An Emotion Feature Extraction Method of BiLSTM-CNN based on Orthogonal Projection
Author(s):
Wei Subo12Zhang Shunxiang12Zhu Guangli12Sun Zhengyan12Li Jian12
(1.School of Computer Science and Engineering, Anhui University of Science and Technology, Huainan 232001, China)
(2.Artificial Intelligence Research Institute of Hefei Comprehensive National Science Center, Hefei 230000, China)
Keywords:
emotional classification orthogonal projection BiLSTM CNN
PACS:
TP391.1
DOI:
10.3969/j.issn.1001-4616.2023.01.018
Abstract:
The emotion feature extraction method of BiLSTM-CNN based on orthogonal projection aims to obtain the weighted neutral word vector from the text,obtain the emotion feature with higher discrimination,and provide strong technical support for text emotion classification. The traditional deep learning model ignores the special meaning of words in the key local context information,resulting in the insufficient acquisition of emotional features. To solve this problem,a BiLSTM-CNN emotion feature extraction method based on orthogonal projection has been proposed. Firstly,the neutral word vector is projected into the orthogonal space of emotional polarity words,and the weighted neutral word vector is obtained. At the same time,the CNN deep learning model is used to extract the key semantics of the text. Then,the BiLSTM-Attention model and weighted neutral word vector are used to learn the semantic features of sentence emotion from the extracted key semantics,which makes the text more discriminative in sentiment classification. The experimental results show that the proposed sentiment feature extraction method can obtain more complete sentiment features,thus significantly improving the accuracy of text sentiment classification.

References:

[1]王汝言,陶中原,赵容剑,等. 多交互图卷积网络用于方面情感分析[J/OL]. 电子与信息学报,2021,43(0):1-8.
[2]ZHANG S X,WEI Z L,WANG Y,et al. Sentiment analysis of Chinese micro-blog text based on extended sentiment dictionary[J]. Future generation computer systems,2018,81:395-403.
[3]FANG Y,TAN H,ZHANG J. Multi-strategy sentiment analysis of consumer reviews based on semantic fuzziness[J]. IEEE access,2018,6:20625-20631.
[4]XU Z,ZHANG S,CHOO K K R,et al. Hierarchy-cutting model based association semantic for analyzing domain topic on the web[J]. IEEE transactions on industrial informatics,2017,13(4):1941-1950.
[5]ZHANG B,XU X,YANG M,et al. Cross-domain sentiment classification by capsule network with semantic rules[J]. IEEE access,2018,6:58284-58294.
[6]MIRTALAIE M A,HUSSAIN O K,CHANG E,et al. Extracting sentiment knowledge from pros/cons product reviews:Discovering features along with the polarity strength of their associated opinions[J]. Expert systems with applications,2018,114:267-288.
[7]陈铁明,缪茹一,王小号. 融合显性和隐性特征的中文微博情感分析[J]. 中文信息学报,2016,30(4):184-192.
[8]ARAQUE O,CORCUERA-PLATAS I,SÁNCHEZ-RADA J F,et al. Enhancing deep learning sentiment analysis with ensemble techniques in social applications[J]. Expert systems with applications,2017,77:236-246.
[9]谢丽星,周明,孙茂松. 基于层次结构的多策略中文微博情感分析和特征抽取[J]. 中文信息学报,2012,26(1):73-83.
[10]李淑芝,余乐陶,邓小鸿.融合深度情感分析和评分矩阵的推荐模型[J]. 电子与信息学报,44(1):245-253.
[11]车思琪,李学沛. 评价系统视阈下中美企业致股东信情感话语对比分析——基于情感词典和机器学习的文本挖掘技术[J]. 外国语(上海外国语大学学报),2021,44(2):50-59.
[12]景丽,李曼曼,何婷婷. 结合扩充词典与自监督学习的网络评论情感分类[J]. 计算机科学,2020,47(11A):78-82,91.
[13]DA'U A,SALIM N,RABIU I,et al. Recommendation system exploiting aspect-based opinion mining with deep learning method[J]. Information sciences,2020,512:1279-1292.
[14]LIAO S,WANG J,YU R,et al. CNN for situations understanding based on sentiment analysis of twitter data[J]. Procedia computer science,2017,111:376-381.
[15]陈飞玥,朱玉莲,陈晓红. 多层特征融合的PCANet及其在人脸识别中的应用[J]. 南京师大学报(自然科学版),2021,166(44):127-133.
[16]金志刚,胡博宏,张瑞. 基于深度学习的多维特征微博情感分析[J]. 中南大学学报(自然科学版),2018,49(5):1135-1140.
[17]CHEN T,XU R,HE Y,et al. Improving sentiment analysis via sentence type classification using BiLSTM-CRF and CNN[J]. Expert systems with applications,2017,72:221-230.
[18]GAO Z,WANG L,ZHOU L,et al. HEp-2 cell image classification with deep convolutional neural networks[J]. IEEE journal of biomedical and health informatics,2016,21(2):416-428.
[19]HUANG B X,CARLEY K. Parameterized convolutional neural networks for aspect level sentiment classification[C]//Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing. New York,NY:ACM,2018:1091-1096.
[20]FAN C,GAO Q,DU J,et al. Convolution-based memory network for aspect-based sentiment analysis[C]//The 41st International ACM SIGIR Conference on Research & Development in Information Retrieval. New York,NY:ACM,2018:1161-1164.
[21]QIN Q,HU W,LIU B. Feature projection for improved text classification[C]//Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. Stroudsburg,PA:ACL,2020:8161-8171.
[22]CONNEAU A,SCHWENK H,BARRAULT L,et al. Very Deep Convolutional Networks for Text Classification[C]//Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics. Stroudsburg,PA:ACL,2017,1:1107-1116.
[23]GANIN Y,LEMPITSKY V. Unsupervised domain adaptation by backpropagation[C]//International Conference on Machine Learning. PMLR,2015,37:1180-1189.
[24]张柯文,李翔,严云洋,等. 基于多特征双向门控神经网络的领域专家实体抽取方法[J]. 南京师大学报(自然科学版),2021,165(44):128-135.

Memo

Memo:
-
Last Update: 2023-03-15