[1]王柳迪,马伟锋,孙晓勇,等.基于双输入和BiLSTM-MHSA的评论文本方面情感分类方法[J].浙江科技学院学报,2023,(05):412-420.[doi:10.3969/j.issn.1671-8798.2023.05.007]
 WANG Liudi,MA Weifeng,SUN Xiaoyong,et al.Aspect-level sentiment classification method for comment texts based on dual input and BiLSTM-MHSA[J].,2023,(05):412-420.[doi:10.3969/j.issn.1671-8798.2023.05.007]
点击复制

基于双输入和BiLSTM-MHSA的评论文本方面情感分类方法(/HTML)
分享到:

《浙江科技学院学报》[ISSN:2097-5236/CN:33-1431/Z]

卷:
期数:
2023年05期
页码:
412-420
栏目:
出版日期:
2023-10-31

文章信息/Info

Title:
Aspect-level sentiment classification method for comment texts based on dual input and BiLSTM-MHSA
文章编号:
1671-8798(2023)05-0412-09
作者:
王柳迪马伟锋孙晓勇王雨晨毛思佳
(浙江科技学院 信息与电子工程学院,杭州 310023)
Author(s):
WANG Liudi MA Weifeng SUN Xiaoyong WANG Yuchen MAO Sijia
(School of Information and Electronic Engineering, Zhejiang University of Science and Technology, Hangzhou 310023, Zhejiang, China)
关键词:
方面词抽取方面情感分类多任务学习用户评论
分类号:
TP391.43
DOI:
10.3969/j.issn.1671-8798.2023.05.007
文献标志码:
A
摘要:
【目的】针对方面情感分类输入类别在不同领域之间差异较大,汽车用户评论文本语义信息不全,语义特征难以提取等问题,提出基于双通道输入的并行双向编码表征(bidirectional encoder representation from transformers,BERT)双向长短期记忆多头自注意力模型的方面情感分类方法。【方法】首先采用了方面情感和方面抽取的双重标签进行标注; 其次通过并行的方面抽取和方面情感分类任务通道,分别使用BERT、双向长短期记忆网络(bidirectional long and short-term memory networks,Bi-LSTM)及多头注意力机制(multihead self-attention,MHSA)提取更深层次的语义信息及近距离和远距离特征信息; 最后采用条件随机场(conditional random field,CRF)分类器和Softmax分类器进行分类。【结果】在相关的汽车用户评论文本数据集和多语言混合数据集上,本研究提出的模型相较于主流的方面情感分类方法,具有同步抽取方面词和判断情感极性的能力,且有效提高了方面词抽取和方面情感分类的准确率和F1值。【结论】本研究提出的模型更有利于汽车销售者分析用户评论,同时对识别用户评论文本的情感极性的研究也有一定的参考价值。

参考文献/References:

[1] 冯志骥.基于文本挖掘的新能源汽车市场研究[D].石家庄:河北经贸大学,2020.
[2] KANWAL S, NAWAZ S, MALIK M K, et al. A review of text-based recommendation systems[J].IEEE Access,2021,31638:1.
[3] KE W, GAO J, SHEN H, et al. Incorporating explicit syntactic dependency for aspect level sentiment classification[J].Neurocomputing,2021,456(16):13.
[4] FAN J, ZHANG X, ZHANG Z, et al. A neural model for aspect-level sentiment classification of product reviews assissted by question-answering[C]//2021 4th International Conference on Advanced Electronic Materials, Computers and Software Engineering(AEMCSE). Changsha:IEEE,2021:643.
[5] LIN P, YANG M, LAI J. Deep selective memory network with selective attention and inter-aspect modeling for aspect level sentiment classification[J].IEEE/ACM Transactions on Audio, Speech, and Language Processing,2021,1093:1.
[6] HE R, LEE W S, NG H T, et al. An unsupervised neural attention model for aspect extraction[C]//Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics. Vancouver:ACL,2017:388.
[7] WANG W, PAN S, DAHLMEIER D, et al. Coupled multi-layer attentions for co-extraction of aspect and opinion terms[C]//Proceedings of the 31th AAAI conference on artificial intelligence. San Francisco:AAAI,2017:1.
[8] SUN Y, QIU H, ZHENG Y, et al. SIFRank:a new baseline for unsupervised keyphrase extraction based on pre-trained language model[J].IEEE Access,2020,8:10896.
[9] LI Y, YIN C, ZHONG S H, et al. Multi-instance multi-label learning networks for aspect-category sentiment analysis[C]//Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing. Punta Cana:EMNLP,2020:3550.
[10] CHEN X, SUN C, WANG J, et al. Aspect sentiment classification with document-level sentiment preference modeling[C]//Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. Seattle:ACL,2020:3667.
[11] CAI H, TU Y, ZHOU X, et al. Aspect-category based sentiment analysis with hierarchical graph convolutional network[C]//Proceedings of the 28th International Conference on Computational Linguistics. Barcelona:ICCL,2020:833.
[12] XU L, CHIA Y K, BING L. Learning span-level interactions for aspect sentiment triplet extraction[C]//Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing. Bangkok:ACL,2021:4755.
[13] DEVLIN J, CHANG M W, LEE K, et al. BERT:pre-training of deep bidirectional transformers for language understanding[C]//Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics:Human Language Technologies. Minneapolis:NAACL,2018:4171.
[14] 周龚雪,马伟锋,龚一飞,等.基于深度学习的交通事故文本因果关系抽取[J].浙江科技学院学报,2022,34(1):10.
[15] LU Y, YAN J. Automatic lip reading using convolution neural network and bidirectional long short-term memory[J].International Journal of Pattern Recognition and Artificial Intelligence,2020,34(1):2054003.
[16] VASWANI A, SHAZEER N, PARMAR N, et al. Attention is all you need[C]//Advances in neural information processing systems. New York:NIPS,2017:30.
[17] CHE W, ZHAO Y, GUO H, et al. Sentence compression for aspect-based sentiment analysis[J].IEEE/ACM Transactions on Audio, Speech, and Language Processing,2015,23(12):2111.
[18] ZHAO Y, PAN H, DU C, et al. Principal curvature for infrared small target detection[J].Infrared Physics & Technology,2015,36:1.
[19] PENG H, MA Y, LI Y, et al. Learning multi-grained aspect target sequence for Chinese sentiment analysis[J].Knowledge-Based Systems,2018,148:167.
[20] PONTIKI M, GALANIS D, PAVLOPOULOS J, et al. SemEval-2014 task 4:aspect based sentiment analysis[J].Proceedings of International Workshop on Semantic Evaluation,2014,27:10.
[21] LI D, WEI F, TAN C, et al. Adaptive recursive neural network for target-dependent twitter sentiment classification[C]//Meeting of the Association for Computational Linguistics. Baltimore:ACL,2014:49.
[22] ISLAM S M, BHATTACHARYA S. AR-BERT:aspect-relation enhanced aspect-level sentiment classification with multi-modal explanations[C]//Proceedings of the ACM Web Conference. Lyon:Association for Computing Machinery,2022:987.
[23] 楼姣,马伟锋,季曹婷,等.基于语义共现与注意力网络的问题分类方法[J].杭州:浙江科技学院学报,2020,32(4):8.
[24] WANG B, SHEN T, LONG G, et al. Eliminating sentiment bias for aspect-level sentiment classification with unsupervised opinion extraction[C]//Findings of the Association for Computational Linguistics. Punta Cana:EMNLP,2021:3002.
[25] WANG Y, HUANG M, ZHU X, et al. Attention-based LSTM for aspect-level sentiment classification[C]//Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing. Austin:ACL,2016:606.
[26] DEVLIN J, CHANG M W, LEE K, et al. BERT:pre-training of deep bidirectional transformers for language understanding[C]//Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics:Human Language Technologie. Minneapolis:NAACL,2018:4171.
[27] LI J, MONROE W, SHI T, et al. Adversarial learning for neural dialogue generation[C]//Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing. Copenhagen:EMNLP,2017:2157.
[28] PENG C, SUN Z, BING L, et al. Recurrent attention network on memory for aspect sentiment analysis[C]//Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing. Copenhagen:EMNLP,2017:452.
[29] SONG Y, WANG J, TAO J, et al. Targeted sentiment classification with attentional encoder network[C]//International Conference on Artificial Neural Networks. Munich:ICANN,2019:93.
[30] XU H, LIU B, SHU L, et al. BERT post-training for review reading comprehension and aspect-based sentiment analysis[C]//Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics:Human Language Technologies. Minneapolis:NAACL,2019:2324.

备注/Memo

备注/Memo:
收稿日期:2022-06-21
基金项目:浙江科技学院企业委托项目(2020KJ272)
通信作者:马伟锋(1979— ),男,浙江省绍兴人,副教授,硕士,主要从事大数据与人工智能应用研究。E-mail:mawf@zust.edu.cn。
更新日期/Last Update: 2023-10-31