Aspect-opinion pair extraction of new energy vehicle complaint text based on context enhancement

doi:10.11772/j.issn.1001-9081.2023081167

Journal of Computer Applications ›› 2024, Vol. 44 ›› Issue (8): 2430-2436.DOI: 10.11772/j.issn.1001-9081.2023081167

• Artificial intelligence • Previous Articles Next Articles

Aspect-opinion pair extraction of new energy vehicle complaint text based on context enhancement

Caiqin WANG¹^,², Yuhao ZHOU¹^,², Shunxiang ZHANG¹^,²(), Yanhui WANG¹^,², Xiaolong WANG¹^,²

^1.School of Computer Science and Engineering，Anhui University of Science & Technology，Huainan Anhui 232001，China
^2.Institute of Artificial Intelligence，Hefei Comprehensive National Science Center，Hefei Anhui 230088，China

Received:2023-08-31 Revised:2023-09-20 Accepted:2023-10-08 Online:2024-08-22 Published:2024-08-10
Contact: Shunxiang ZHANG
About author:WANG Caiqin ， born in 2000， M. S. candidate. His researchinterests include sentiment analysis， Web mining.
ZHOU Yuhao ， born in 2000， M. S. candidate. His researchinterests include sentiment analysis， data mining.
ZHANG Shunxiang ， born in 1970， Ph. D.， professor. Hisresearch interests include Web mining， semantic search， relationextraction， complex network analysis.
WANG Yanhui， born in 1999， M. S. candidate. Her researchinterests include sentiment analysis， relation extraction.
WANG Xiaolong， born in 1999， M. S. candidate. His researchinterests include natural language processing， Web mining.
Supported by:
This work was partially supported by National Natural ScienceFoundation of China （62076006）； University Synergy InnovationProgram of Anhui Province（ GXXT-2021-008）.

基于语境增强的新能源汽车投诉文本方面-观点对抽取

汪才钦¹^,², 周渝皓¹^,², 张顺香¹^,²(), 王琰慧¹^,², 王小龙¹^,²

^1.安徽理工大学计算机科学与工程学院，安徽淮南 232001
^2.合肥综合性国家科学中心人工智能研究院，合肥 230088

通讯作者: 张顺香
作者简介:汪才钦（2000—），男，安徽六安人，硕士研究生，CCF会员，主要研究方向：情感分析、Web挖掘
周渝皓（2000—），男，山东济南人，硕士研究生，主要研究方向：情感分析、数据挖掘
张顺香（1970—），男，安徽无为人，教授，博士，主要研究方向：Web挖掘、语义搜索、关系抽取、复杂网络分析 sxzhang@aust.edu.cn
王琰慧（1999—），女，山东淄博人，硕士研究生，CCF会员，主要研究方向：情感分析、关系抽取
王小龙（1999—），男，安徽阜阳人，硕士研究生，CCF会员，主要研究方向：自然语言处理、Web挖掘。
基金资助:
国家自然科学基金资助项目(62076006);安徽高校协同创新项目(GXXT?2021?008)

Abstract

Abstract:

Mining users’ multi-dimensional opinions on products from the complaint texts of new energy vehicles can provide support for product design decisions. Because the complaint text has the characteristics of high entity density and lengthy sentence structure， the existing methods for Aspect-Opinion Pair Extraction （AOPE） suffer from weak correlations between aspect terms and opinion terms. To address this problem， an Aspect-Opinion pair Extraction model based on Context Enhancement （AOE-CE） was proposed， fusing topic features and text features as contextual representation to enhance the correlations between entities. This model was consisted of an entity recognition module and a relation detection module. Firstly， in the entity recognition module， the text was encoded by using a pre-trained model and a part-of-speech tagging tool. Secondly， Bi-directional Long Short-Term Memory （Bi-LSTM） network combined with multi-head attention was employed to capture contextual information and then derive text features. Subsequently， these text features were input into a Conditional Random Field （CRF） model to obtain the entity set. In the relation detection module， the topic features were obtained through BERT （Bidirectional Encoder Representations from Transformers） and fused with the text features to obtain the enhanced contextual representation. Then the tri-affine mechanism was used to enhance the correlations between entities with the help of contextual representation. Finally， the extraction result was obtained by Sigmoid. The experimental results show that the precision， recall， and F1 value of AOE-CE are 2.19， 1.08， and 1.60 percentage points higher than those of SDRN （Synchronous Double-channel Recurrent Network） model respectively， indicating that AOE-CE has better AOPE effect.

Key words: Aspect-Opinion Pair Extraction (AOPE), new energy vehicle, complaint text, context enhancement, tri-affine mechanism, multi-head attention

摘要：

挖掘新能源汽车投诉文本中用户对产品多维度的意见，能为产品的设计决策提供参考。因投诉文本具有实体密度高、句式冗长等特点，导致当前方面-观点对抽取（AOPE）方法感知方面项与观点项间的关联性不强。针对这一问题，提出一种基于语境增强的AOPE模型（AOE-CE），通过融合主题特征与文本特征作为语境表示增强实体间的关联关系。模型由实体识别和关系检测2个模块组成：首先，实体识别通过预训练模型和词性标注工具编码文本，再利用双向长短期记忆（Bi-LSTM）网络结合多头注意力捕获上下文信息得到文本特征，并将文本特征输入至条件随机场（CRF）得到实体集合；关系检测通过BERT（Bidirectional Encoder Representations from Transformers）获取主题特征，并将主题特征与文本特征融合获得增强的语境表示，再利用三仿射机制以语境表示为辅助增强实体间的关联关系，最后通过Sigmoid得到抽取结果。实验结果表明，AOE-CE的精准率、召回率和F1值比SDRN（Synchronous Double-channel Recurrent Network）模型分别提升了2.19、1.08和1.60个百分点，表明所提模型具有更好的AOPE效果。

关键词: 方面-观点对抽取, 新能源汽车, 投诉文本, 语境增强, 三仿射机制, 多头注意力

CLC Number:

TP391

Caiqin WANG, Yuhao ZHOU, Shunxiang ZHANG, Yanhui WANG, Xiaolong WANG. Aspect-opinion pair extraction of new energy vehicle complaint text based on context enhancement[J]. Journal of Computer Applications, 2024, 44(8): 2430-2436.

汪才钦, 周渝皓, 张顺香, 王琰慧, 王小龙. 基于语境增强的新能源汽车投诉文本方面-观点对抽取[J]. 《计算机应用》唯一官方网站, 2024, 44(8): 2430-2436.

Figures/Tables 10

References 28

1	刘永相，李彦斌，林亮，等.基于区块链的共享汽车智能合约算法设计［J］.计算机应用，2020，40（S1）：231-237.
	LIU Y X， LI Y B， LIN L， et al. Design of smart contract algorithm for shared vehicle based on blockchain［J］. Journal of Computer Applications， 2020， 40（S1）： 231-237.
2	WU A. Collaborative eco-innovation and green knowledge acquisition： the role of specific investments in Chinese new energy vehicle industry［J］. Business Strategy and the Environment， 2023， 32（4）： 2245-2260.
3	CHEN S， LIU J， WANG Y， et al. Synchronous double-channel recurrent network for aspect-opinion pair extraction［C］// Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. Stroudsburg： ACL， 2020： 6515-6524.
4	ZHAO H， HUANG L， ZHANG R， et al. SpanMlt： a span-based multi-task learning framework for pair-wise aspect and opinion terms extraction［C］// Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. Stroudsburg： ACL，2020： 3239-3248.
5	WU Z， YING C， ZHAO F， et al. Grid tagging scheme for aspect-oriented fine-grained opinion extraction［EB/OL］.（2020-10-09）［2023-06-18］..
6	PHAN H T， NGUYEN N T， HWANG D. Aspect-level sentiment analysis： a survey of graph convolutional network methods［J］. Information Fusion， 2023， 91： 149-172.
7	ZHANG S， JIA W-J， XIA Y-J， et al. Opinion analysis of product reviews［C］// Proceedings of the 2009 6th International Conference on Fuzzy Systems and Knowledge Discovery. Piscataway： IEEE， 2009： 591-595.
8	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.
9	刘欢，窦全胜.嵌入不同邻域表征的方面级情感分析模型［J］.计算机应用，2023， 43（1）： 37-44.
	LIU H， DOU Q S. Aspect-based sentiment analysis model embedding different neighborhood representations ［J］. Journal of Computer Applications， 2023，43（1）：37-44.
10	张世奇，马进，周夏冰，等.基于预训练语言模型的商品属性抽取［J］.中文信息学报， 2022， 36（1）： 56-64.
	ZHANG S Q， MA J， ZHOU X B， et al. Pre-trained language models for product attribute extraction［J］. Journal of Chinese Information Processing， 2022， 36（1）： 56-64.
11	BHAMARE B R， PRABHU J. A supervised scheme for aspect extraction in sentiment analysis using the hybrid feature set of word dependency relations and lemmas［J］. PeerJ Computer Science， 2021， 7： e347.
12	苏明星，吴厚月，李健，等.基于多层交互注意力机制的商品属性抽取［J］.数据分析与知识发现，2023，7（2）：108-118.
	SU M X， WU H Y， LI J， et al. AEMIA： extracting commodity attributes based on multi-level interactive attention mechanism［J］. Data Analysis and Knowledge Discovery， 2023， 7（2）： 108-118.
13	潘雨晨，尉桢楷，洪宇，等.融合高频属性信息的属性抽取研究［J］.中文信息学报， 2023， 37（1）： 132-143.
	PAN Y C， YU Z K， HONG Y， et al. Aspect extraction via high-frequency aspects［J］. Journal of Chinese Information Processing， 2023， 37（1）：132-143.
14	DAI H， SONG Y. Neural aspect and opinion term extraction with mined rules as weak supervision［C］// Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. Stroudsburg： ACL， 2019： 5268-5277.
15	WU S， WU F， CHANG Y， et al. Automatic construction of target-specific sentiment lexicon［J］. Expert Systems with Applications， 2019， 116： 285-298.
16	WANG Y， HE W， JIANG M， et al. CHOpinionMiner： an unsupervised system for Chinese opinion target extraction［J］. Concurrency and Computation： Practice and Experience， 2020， 32（7）： e5582.
17	李宏宇，段利国，候晨蕾，等.基于CWHC-AM的实体及关系联合抽取方法［J］.中文信息学报，2022， 36（11）： 79-90.
	LI H Y， DUAN L G， HOU C L， et al. Joint extraction of entities and relations based on CWHC-AM ［J］. Journal of Chinese Information Processing， 2022， 36（11）： 79-90.
18	XU H， ZHANG S， ZHU G， et al. ALSEE： a framework for attribute-level sentiment element extraction towards product reviews［J］. Connection Science， 2022， 34（1）： 205-223.
19	HU M， PENG Y， HUANG Z， et al. Open-domain targeted sentiment analysis via span-based extraction and classification［C］// Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. Stroudsburg： ACL， 2019： 537-546.
20	KUMAR A， VEERUBHOTLA A S， NARAPAREDDY V T， et al. Aspect term extraction for opinion mining using a hierarchical self-attention network［J］. Neurocomputing， 2021， 465： 195-204.
21	陈林颖，刘建华，孙水华，等.面向方面的自适应跨度特征的细粒度意见元组提取［J］.计算机应用， 2023， 43（5）： 1454-1460.
	CHEN L Y， LIU J H， SUN S H， et al. Aspect-oriented fine-grained opinion tuple extraction with adaptive span features［J］. Journal of Computer Applications， 2023， 43（5）： 1454-1460.
22	WU S， FEI H， REN Y， et al. Learn from syntax： improving pair-wise aspect and opinion terms extraction with rich syntactic knowledge［EB/OL］.（2021-05-06）［2023-06-18］. .
23	ZHANG Y， PENG T， HAN R， et al. Synchronously tracking entities and relations in a syntax-aware parallel architecture for aspect-opinion pair extraction［J］. Applied Intelligence， 2022， 52（13）： 15210-15225.
24	廖黾，刘德喜，万常选，等.目标语义与位置融合的方面意见词抽取［J］.小型微型计算机系统， 2022，43（9）：1908-1917.
	LIAO M， LIU D X， WAN C X， et al. Target-oriented opinion word extraction based on the fusion of aspect target semantics and position［J］. Journal of Chinese Computer Systems， 2022， 43（9）： 1908-1917.
25	李阳，唐积强，朱俊武，等.KENAOTE：一种知识增强的方面和意见对提取多任务学习模型［J］.计算机应用研究， 2023， 40（2）： 359-364.
	LI Y， TANG J Q， ZHU J W， et al. KENAOTE： multi-task learning model for knowledge augmented aspect and opinion pair extraction［J］. Application Research of Computers， 2023， 40（2）： 359-364.
26	ZHANG C， LI Q， SONG D， et al. A multi-task learning framework for opinion triplet extraction［EB/OL］.（2020-10-04）［2023-06-18］..
27	HE R， LEE W S， NG H T， et al. An interactive multi-task learning network for end-to-end aspect-based sentiment analysis［C］// Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. Stroudsburg： ACL， 2019： 504-515.
28	BEKOULIS G， DELEU J， DEMEESTER T， et al. Joint entity recognition and relation extraction as a multi-head selection problem［J］. Expert Systems with Applications， 2018， 114： 34-45.

类别	投诉文本数	方面项数	观点项数
训练集	3 744	16 848	19 860
测试集	468	2 206	2 667
验证集	468	2 160	2 610

类别	投诉文本数	方面项数	观点项数
训练集	3 744	16 848	19 860
测试集	468	2 206	2 667
验证集	468	2 160	2 610

模型	P	R	F1	模型	P	R	F1
BiLSTM-CRF	62.61	60.86	61.72	SpanMIt	71.66	65.75	68.58
HAST+TOWE	64.25	61.14	62.66	GTS	73.36	69.72	71.49
JERE-MHS	67.24	63.85	65.50	SDRN	74.23	70.28	72.20
RINANTE	70.52	66.65	68.53	AOE⁃CE	76.42	71.36	73.80

模型	P	R	F1	模型	P	R	F1
BiLSTM-CRF	62.61	60.86	61.72	SpanMIt	71.66	65.75	68.58
HAST+TOWE	64.25	61.14	62.66	GTS	73.36	69.72	71.49
JERE-MHS	67.24	63.85	65.50	SDRN	74.23	70.28	72.20
RINANTE	70.52	66.65	68.53	AOE⁃CE	76.42	71.36	73.80

模型	P	R	F1	模型	P	R	F1
AOE-Context	72.20	65.82	68.86	AOE-POS	74.54	68.72	71.51
AOE-Topic	73.86	66.58	70.03	AOE-MHA	75.32	70.24	72.70
AOE-Text	74.12	66.93	70.34	AOE⁃CE	76.42	71.36	73.80

Aspect-opinion pair extraction of new energy vehicle complaint text based on context enhancement

基于语境增强的新能源汽车投诉文本方面-观点对抽取

RichHTML

PDF

Knowledge

Abstract

Cite this article

share this article

Figures/Tables 10

References 28

Related Articles 10

Recommended Articles

Metrics

[1]	Pengqi GAO, Heming HUANG, Yonghong FAN. Fusion of coordinate and multi-head attention mechanisms for interactive speech emotion recognition [J]. Journal of Computer Applications, 2024, 44(8): 2400-2406.
[2]	Hao CHAO, Shuqi FENG, Yongli LIU. Convolutional recurrent neural network optimized by multiple context vectors in EEG-based emotion recognition [J]. Journal of Computer Applications, 2024, 44(7): 2041-2046.
[3]	Yushan JIANG, Yangsen ZHANG. Large language model-driven stance-aware fact-checking [J]. Journal of Computer Applications, 2024, 44(10): 3067-3073.
[4]	Kai ZHANG, Zhengchu QIN, Yue LIU, Xinyi QIN. Multi-learning behavior collaborated knowledge tracing model [J]. Journal of Computer Applications, 2023, 43(5): 1422-1429.
[5]	Anqin ZHANG, Xiaohui WANG. Power battery safety warning based on time series anomaly detection [J]. Journal of Computer Applications, 2023, 43(12): 3799-3805.
[6]	Hong YANG, He ZHANG, Shaoning JIN. Human pose transfer model combining convolution and multi-head attention [J]. Journal of Computer Applications, 2023, 43(11): 3403-3410.
[7]	Dan XU, Hongfang GONG, Rongrong LUO. Aspect sentiment analysis with aspect item and context representation [J]. Journal of Computer Applications, 2023, 43(10): 3086-3092.
[8]	Lei YANG, Hongdong ZHAO, Kuaikuai YU. End-to-end speech emotion recognition based on multi-head attention [J]. Journal of Computer Applications, 2022, 42(6): 1869-1875.
[9]	Zhijin LI, Hua LAI, Yonghua WEN, Shengxiang GAO. Neural machine translation integrating bidirectional-dependency self-attention mechanism [J]. Journal of Computer Applications, 2022, 42(12): 3679-3685.
[10]	Yu DENG, Xiaoyu LI, Jian CUI, Qi LIU. Multi-head attention memory network for short text sentiment classification [J]. Journal of Computer Applications, 2021, 41(11): 3132-3138.