Knowledge-guided multi-granularity GCN for ABSA

Aspect-based sentiment analysis aims to determine sentiment polarities toward specific aspect terms within the same sentence or document. Most recent studies adopted attention-based neural network models to implicitly connect aspect terms with context words. However, these studies were limited by in...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:Information processing & management Ročník 60; číslo 2; s. 103223
Hlavní autoři: Zhu, Zhenfang, Zhang, Dianyuan, Li, Lin, Li, Kefeng, Qi, Jiangtao, Wang, Wenling, Zhang, Guangyuan, Liu, Peiyu
Médium: Journal Article
Jazyk:angličtina
Vydáno: Elsevier Ltd 01.03.2023
Témata:
ISSN:0306-4573, 1873-5371
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Abstract Aspect-based sentiment analysis aims to determine sentiment polarities toward specific aspect terms within the same sentence or document. Most recent studies adopted attention-based neural network models to implicitly connect aspect terms with context words. However, these studies were limited by insufficient interaction between aspect terms and opinion words, leading to poor performance on robustness test sets. In addition, we have found that robustness test sets create new sentences that interfere with the original information of a sentence, which often makes the text too long and leads to the problem of long-distance dependence. Simultaneously, these new sentences produce more non-target aspect terms, misleading the model because of the lack of relevant knowledge guidance. This study proposes a knowledge guided multi-granularity graph convolutional neural network (KMGCN) to solve these problems. The multi-granularity attention mechanism is designed to enhance the interaction between aspect terms and opinion words. To address the long-distance dependence, KMGCN uses a graph convolutional network that relies on a semantic map based on fine-tuning pre-trained models. In particular, KMGCN uses a mask mechanism guided by conceptual knowledge to encounter more aspect terms (including target and non-target aspect terms). Experiments are conducted on 12 SemEval-2014 variant benchmarking datasets, and the results demonstrated the effectiveness of the proposed framework. •This paper proposes a knowledge guided multi-granularity graph convolutional neural network (KMGCN) to solve these problems.•Multi-granularity attention mechanism is designed to enhance the interaction between the aspect terms and the opinion words.•In order to deal with the problem of long distance dependence, KMGCN uses a graph convolutional network that relies on the semantic map based on fine-tuning pre-training.•In particular, KMGCN uses a mask mechanism guided by conceptual knowledge to face with new aspect terms.
AbstractList Aspect-based sentiment analysis aims to determine sentiment polarities toward specific aspect terms within the same sentence or document. Most recent studies adopted attention-based neural network models to implicitly connect aspect terms with context words. However, these studies were limited by insufficient interaction between aspect terms and opinion words, leading to poor performance on robustness test sets. In addition, we have found that robustness test sets create new sentences that interfere with the original information of a sentence, which often makes the text too long and leads to the problem of long-distance dependence. Simultaneously, these new sentences produce more non-target aspect terms, misleading the model because of the lack of relevant knowledge guidance. This study proposes a knowledge guided multi-granularity graph convolutional neural network (KMGCN) to solve these problems. The multi-granularity attention mechanism is designed to enhance the interaction between aspect terms and opinion words. To address the long-distance dependence, KMGCN uses a graph convolutional network that relies on a semantic map based on fine-tuning pre-trained models. In particular, KMGCN uses a mask mechanism guided by conceptual knowledge to encounter more aspect terms (including target and non-target aspect terms). Experiments are conducted on 12 SemEval-2014 variant benchmarking datasets, and the results demonstrated the effectiveness of the proposed framework. •This paper proposes a knowledge guided multi-granularity graph convolutional neural network (KMGCN) to solve these problems.•Multi-granularity attention mechanism is designed to enhance the interaction between the aspect terms and the opinion words.•In order to deal with the problem of long distance dependence, KMGCN uses a graph convolutional network that relies on the semantic map based on fine-tuning pre-training.•In particular, KMGCN uses a mask mechanism guided by conceptual knowledge to face with new aspect terms.
ArticleNumber 103223
Author Zhu, Zhenfang
Li, Lin
Zhang, Guangyuan
Wang, Wenling
Li, Kefeng
Liu, Peiyu
Qi, Jiangtao
Zhang, Dianyuan
Author_xml – sequence: 1
  givenname: Zhenfang
  surname: Zhu
  fullname: Zhu, Zhenfang
  email: zhuzf@sdjtu.edu.cn
  organization: School of Information Science and Electrical Engineering, Shandong Jiao Tong University, Jinan 250357, China
– sequence: 2
  givenname: Dianyuan
  surname: Zhang
  fullname: Zhang, Dianyuan
  email: csdzdy@163.com
  organization: School of Information Science and Electrical Engineering, Shandong Jiao Tong University, Jinan 250357, China
– sequence: 3
  givenname: Lin
  surname: Li
  fullname: Li, Lin
  email: cathylilin@whut.edu.cn
  organization: School of Computer and Artificial Intelligence, Wuhan University of Technology, Wuhan 430070, China
– sequence: 4
  givenname: Kefeng
  surname: Li
  fullname: Li, Kefeng
  email: 205073@sdjtu.edu.cn
  organization: School of Information Science and Electrical Engineering, Shandong Jiao Tong University, Jinan 250357, China
– sequence: 5
  givenname: Jiangtao
  surname: Qi
  fullname: Qi, Jiangtao
  email: qijiangtaohappy@hotmail.com
  organization: School of Information Science and Electrical Engineering, Shandong Jiao Tong University, Jinan 250357, China
– sequence: 6
  givenname: Wenling
  surname: Wang
  fullname: Wang, Wenling
  email: 362607793@qq.com
  organization: Chinese Lexicography Research Center, Lu Dong University, Yantai 264025, China
– sequence: 7
  givenname: Guangyuan
  surname: Zhang
  fullname: Zhang, Guangyuan
  email: xdzhanggy@163.com
  organization: School of Information Science and Electrical Engineering, Shandong Jiao Tong University, Jinan 250357, China
– sequence: 8
  givenname: Peiyu
  surname: Liu
  fullname: Liu, Peiyu
  email: liupy@sdnu.edu.cn
  organization: School of Information Science and Engineering, Shandong Normal University, Jinan 250358, China
BookMark eNp9j81KAzEYRYNUsK0-gLt5gbTJl8wkg6uxaBWLLtR1SJNMSZmfkskofftOGVcuurrcC-fCmaFJ0zYOoXtKFpTQbLlf-EO9AAIwdAbArtCUSsFwygSdoClhJMM8FewGzbpuTwjhKYUpWr417W_l7M7hXe-ts0ndV9HjXdBNX-ng4zFZr96Tsg1J8fhZ3KLrUledu_vLOfp-fvpaveDNx_p1VWywgVxELEUmgRIQFmCbW1lKnXHOWJoZy2RmeC4Jp0JuqSQ540OUJRfgUtDDximbIzr-mtB2XXClOgRf63BUlKizsdqrwVidjdVoPDDiH2N81NG3TQzaVxfJh5F0g9KPd0F1xrvGOOuDM1HZ1l-gTzzjbyk
CitedBy_id crossref_primary_10_1007_s10489_025_06257_z
crossref_primary_10_4018_IJSWIS_336921
crossref_primary_10_3389_fpls_2023_1227011
crossref_primary_10_1007_s12559_025_10497_z
crossref_primary_10_1007_s11227_024_06524_9
crossref_primary_10_1007_s11042_024_18431_5
crossref_primary_10_1109_ACCESS_2025_3577048
crossref_primary_10_1016_j_inffus_2024_102747
crossref_primary_10_1109_TAFFC_2024_3430045
crossref_primary_10_1016_j_ipm_2023_103539
crossref_primary_10_1038_s41598_025_08914_2
crossref_primary_10_1049_ipr2_13215
crossref_primary_10_3390_math12020317
crossref_primary_10_1016_j_asoc_2025_113707
crossref_primary_10_1016_j_eswa_2025_129034
crossref_primary_10_1007_s12598_024_02942_z
crossref_primary_10_1049_ipr2_13310
crossref_primary_10_1016_j_inffus_2025_103078
crossref_primary_10_1016_j_eswa_2024_124854
crossref_primary_10_1109_ACCESS_2024_3430092
crossref_primary_10_1007_s11227_025_07273_z
crossref_primary_10_1016_j_bspc_2024_106944
crossref_primary_10_3389_fnbot_2023_1281166
crossref_primary_10_1007_s13042_025_02673_2
crossref_primary_10_1109_TCSS_2023_3296476
crossref_primary_10_1109_TETCI_2025_3537918
crossref_primary_10_1016_j_neucom_2025_131137
crossref_primary_10_1016_j_knosys_2023_111345
crossref_primary_10_1016_j_ipm_2024_103988
crossref_primary_10_1007_s10489_025_06232_8
crossref_primary_10_1007_s10660_025_09978_y
crossref_primary_10_1016_j_knosys_2023_110877
crossref_primary_10_1016_j_knosys_2025_113279
crossref_primary_10_1109_TCSS_2023_3303027
crossref_primary_10_1109_TAFFC_2024_3360979
crossref_primary_10_1016_j_eswa_2024_126062
crossref_primary_10_1016_j_imavis_2024_105172
crossref_primary_10_1007_s10844_024_00881_w
crossref_primary_10_1109_TFUZZ_2025_3583050
crossref_primary_10_1016_j_ipm_2023_103500
crossref_primary_10_1109_ACCESS_2025_3567845
crossref_primary_10_1016_j_knosys_2024_112629
crossref_primary_10_1007_s10489_023_04588_3
crossref_primary_10_1016_j_ipm_2024_104055
crossref_primary_10_3390_electronics13163263
crossref_primary_10_1016_j_neunet_2025_107758
crossref_primary_10_1016_j_asoc_2025_112763
crossref_primary_10_1016_j_ins_2024_121561
crossref_primary_10_3390_electronics13030517
crossref_primary_10_1007_s00371_024_03722_7
crossref_primary_10_1007_s10489_024_05492_0
crossref_primary_10_1016_j_neucom_2025_129842
crossref_primary_10_1016_j_ipm_2023_103508
crossref_primary_10_1016_j_neucom_2025_131037
crossref_primary_10_1016_j_jksuci_2023_101651
crossref_primary_10_1186_s40537_025_01068_y
crossref_primary_10_3390_s23208426
Cites_doi 10.18653/v1/2021.emnlp-main.552
10.1016/j.aiopen.2021.01.001
10.18653/v1/P18-1087
10.18653/v1/S16-1002
10.1109/TNNLS.2020.2978386
10.1609/aaai.v29i1.9491
10.18653/v1/2021.naacl-main.231
10.1109/CVPR.2017.195
10.1109/MS.2011.122
10.18653/v1/2020.acl-main.295
10.1109/TKDE.2017.2754499
10.3115/1073083.1073092
10.18653/v1/2021.emnlp-main.22
10.1145/3331184.3331351
10.18653/v1/2020.emnlp-main.292
10.18653/v1/P18-1076
10.1016/j.knosys.2016.06.009
10.1016/j.knosys.2021.107643
10.18653/v1/2021.naacl-main.146
10.1109/TKDE.2015.2485209
10.1145/3178876.3186175
10.1016/j.knosys.2019.105443
10.18653/v1/D18-1136
10.18653/v1/2020.acl-main.293
10.3115/v1/P15-1026
10.18653/v1/D18-1380
10.18653/v1/D16-1021
10.1145/1871437.1871689
10.1109/TASLP.2020.3017093
10.1145/1864708.1864770
10.24963/ijcai.2017/568
10.18653/v1/P18-1234
10.3390/app9163389
10.1145/3209978.3210081
ContentType Journal Article
Copyright 2022 Elsevier Ltd
Copyright_xml – notice: 2022 Elsevier Ltd
DBID AAYXX
CITATION
DOI 10.1016/j.ipm.2022.103223
DatabaseName CrossRef
DatabaseTitle CrossRef
DatabaseTitleList
DeliveryMethod fulltext_linktorsrc
Discipline Library & Information Science
EISSN 1873-5371
ExternalDocumentID 10_1016_j_ipm_2022_103223
S0306457322003247
GroupedDBID --K
--M
-~X
.DC
.~1
0B8
0R~
1B1
1RT
1~.
1~5
29I
4.4
41~
457
4G.
5GY
5VS
7-5
71M
77K
8P~
9JN
9JO
AABNK
AACTN
AAEDT
AAEDW
AAFJI
AAIAV
AAIKJ
AAKOC
AALRI
AAOAW
AAQFI
AAQXK
AAXUO
AAYFN
AAYOK
ABBOA
ABFNM
ABFRF
ABJNI
ABMAC
ABMMH
ABPPZ
ABXDB
ABYKQ
ACDAQ
ACGFS
ACHQT
ACNNM
ACRLP
ACZNC
ADBBV
ADEZE
ADJOM
ADMUD
AEBSH
AEFWE
AEKER
AENEX
AFKWA
AFTJW
AGHFR
AGUBO
AGYEJ
AHHHB
AHZHX
AIALX
AIEXJ
AIKHN
AITUG
AJBFU
AJOXV
AKYCK
ALMA_UNASSIGNED_HOLDINGS
AMFUW
AMRAJ
AOMHK
AOUOD
ASPBG
AVARZ
AVWKF
AXJTR
AZFZN
BKOJK
BLXMC
CS3
DU5
EBS
EFJIC
EFLBG
EJD
EO8
EO9
EP2
EP3
FDB
FEDTE
FGOYB
FIRID
FNPLU
FYGXN
G-2
G-Q
GBLVA
GBOLZ
HLZ
HMY
HVGLF
HZ~
H~9
IHE
J1W
KOM
LG9
LPU
LY1
M3Y
M41
MO0
MS~
MVM
N9A
O-L
O9-
OAUVE
OHT
OZT
P-8
P-9
P2P
PC.
PQQKQ
PRBVW
Q38
R2-
RIG
ROL
RPZ
SBC
SDF
SDG
SDP
SDS
SES
SEW
SPC
SPCBC
SSB
SSO
SSS
SSV
SSZ
T5K
TN5
U5U
UHB
UHS
UNMZH
WUQ
XFK
ZMT
~G-
77I
9DU
AATTM
AAXKI
AAYWO
AAYXX
ABWVN
ACLOT
ACRPL
ACVFH
ADCNI
ADMHG
ADNMO
AEIPS
AEUPX
AFJKZ
AFPUW
AGQPQ
AIGII
AIIUN
AKBMS
AKRWK
AKYEP
ANKPU
APXCP
CITATION
EFKBS
~HD
ID FETCH-LOGICAL-c297t-876821027d22b9d8f8a6443356cd386c49804178b180934b18ff472e52a8b1413
ISICitedReferencesCount 67
ISICitedReferencesURI http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000961166400001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN 0306-4573
IngestDate Tue Nov 18 21:54:59 EST 2025
Sat Nov 29 07:24:02 EST 2025
Fri Feb 23 02:39:36 EST 2024
IsPeerReviewed true
IsScholarly true
Issue 2
Keywords Sentiment analysis
Attention mechanism
Conceptual knowledge
Robustness analysis
Graph neural network
Language English
LinkModel OpenURL
MergedId FETCHMERGED-LOGICAL-c297t-876821027d22b9d8f8a6443356cd386c49804178b180934b18ff472e52a8b1413
ParticipantIDs crossref_primary_10_1016_j_ipm_2022_103223
crossref_citationtrail_10_1016_j_ipm_2022_103223
elsevier_sciencedirect_doi_10_1016_j_ipm_2022_103223
PublicationCentury 2000
PublicationDate March 2023
2023-03-00
PublicationDateYYYYMMDD 2023-03-01
PublicationDate_xml – month: 03
  year: 2023
  text: March 2023
PublicationDecade 2020
PublicationTitle Information processing & management
PublicationYear 2023
Publisher Elsevier Ltd
Publisher_xml – name: Elsevier Ltd
References (pp. 293–296).
Ferragina, P., & Scaiella, U. (2010). Tagme: On-the-fly annotation of short text fragments (by Wikipedia entities). In
Wu, Pan, Chen, Long, Zhang, Philip (b39) 2020; 32
Lin, Y., Liu, Z., Sun, M., Liu, Y., & Zhu, X. (2015). Learning entity and relation embeddings for knowledge graph completion. In
Ferragina, Scaiella (b9) 2011; 29
Zhao, Sun, Xu, Zhang, Luo (b47) 2019
(pp. 4171–4186).
Vaswani, Shazeer, Parmar, Uszkoreit, Jones, Gomez (b33) 2017
(pp. 2910–2922).
(pp. 4068–4074).
(pp. 3594–3605).
(pp. 1145–1148).
(pp. 946–956).
Phan, M. H., & Ogunbona, P. O. (2020). Modelling Context and Syntactical Features for Aspect-based Sentiment Analysis. In
(pp. 3433–3442).
Gao, T., Yao, X., & Chen, D. (2021). SimCSE: Simple Contrastive Learning of Sentence Embeddings. In
Shen, Y., Deng, Y., Yang, M., Li, Y., Du, N., Fan, W., et al. (2018). Knowledge-aware attentive neural network for ranking question answer pairs. In
Ma, D., Li, S., Zhang, X., & Wang, H. (2017). Interactive attention networks for aspect-level sentiment classification. In
(pp. 260–269).
Huang, B., & Carley, K. M. (2018). Parameterized Convolutional Neural Networks for Aspect Level Sentiment Classification. In
Song, Wang, Jiang, Liu, Rao (b30) 2019
Ma, Zhang, Song (b21) 2021
(pp. 2514–2523).
Gui, Wang, Zhang, Liu, Zou, Zhou (b12) 2021
Li, X., Bing, L., Lam, W., & Shi, B. (2018). Transformation Networks for Target-Oriented Sentiment Classification. In
(pp. 1251–1258).
Zhang, C., Li, Q., & Song, D. (2019b). Syntax-aware aspect-level sentiment classification with proximity-weighted convolution network. In
(pp. 774–784).
Xing, X., Jin, Z., Jin, D., Wang, B., Zhang, Q., & Huang, X. J. (2020). Tasty Burgers, Soggy Fries: Probing Aspect Robustness in Aspect-Based Sentiment Analysis. In
.
Wang, K., Shen, W., Yang, Y., Quan, X., & Wang, R. (2020). Relational Graph Attention Network for Aspect-based Sentiment Analysis. In
(pp. 6894–6910).
(pp. 901–904).
Gu, S., Zhang, L., Hou, Y., & Song, Y. (2018). A position-aware bidirectional attention network for aspect-level sentiment analysis. In
Ravichandran, D., & Hovy, E. (2002). Learning surface text patterns for a question answering system. In
(pp. 1816–1829).
Zhang, Li, Song (b43) 2019
Fan, F., Feng, Y., & Zhao, D. (2018). Multi-grained attention network for aspect-level sentiment classification. In
(pp. 821–832).
(pp. 1091–1096).
Poria, Cambria, Gelbukh (b25) 2016; 108
Bahdanau, D., Cho, K. H., & Bengio, Y. (2015). Neural machine translation by jointly learning to align and translate. In
Davidson, J., Liebald, B., Liu, J., Nandy, P., Van Vleet, T., Gargi, U., et al. (2010). The YouTube video recommendation system. In
Wang, Mao, Wang, Guo (b34) 2017; 29
Wang, H., Zhang, F., Xie, X., & Guo, M. (2018). DKN: Deep knowledge-aware network for news recommendation. In
Sheu, Chu, Qi, Li (b29) 2021
Tian, Y., Chen, G., & Song, Y. (2021). Aspect-based Sentiment Analysis with Type-aware Graph Convolutional Networks and Layer Ensemble. In
Liang, Su, Gui, Cambria, Xu (b17) 2022; 235
(pp. 3211–3220).
Tang, D., Qin, B., & Liu, T. (2016). Aspect Level Sentiment Classification with Deep Memory Network. In
Chollet, F. (2017). Xception: Deep learning with depthwise separable convolutions. In
Dong, L., Wei, F., Zhou, M., & Xu, K. (2015). Question answering over freebase with multi-column convolutional neural networks. In
(pp. 1625–1628).
(pp. 41–47).
(pp. 1121–1131).
(pp. 19–30).
He, R., Lee, W. S., Ng, H. T., & Dahlmeier, D. (2018). Effective attention modeling for aspect-level sentiment classification. In
Devlin, J., Chang, M. W., Lee, K., & Toutanova, K. (2019). BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In
(pp. 246–256).
Xue, W., & Li, T. (2018). Aspect Based Sentiment Analysis with Gated Convolutional Networks. In
Zhang, Li, Xu, Leung, Chen, Ye (b45) 2020; 28
Pontiki, M., Galanis, D., Papageorgiou, H., Androutsopoulos, I., Manandhar, S., Al-Smadi, M., et al. (2016). Semeval-2016 task 5: Aspect based sentiment analysis. In
Zhou, Cui, Hu, Zhang, Yang, Liu (b48) 2020; 1
(pp. 3229–3238).
Wu, Fan, Baevski, Dauphin, Auli (b38) 2019
(pp. 214–224).
(pp. 1835–1844).
Schouten, Frasincar (b27) 2015; 28
Dai, J., Yan, H., Sun, T., Liu, P., & Qiu, X. (2021). Does syntax matter? A strong baseline for Aspect-based Sentiment Analysis with RoBERTa. In
Zhao, Hou, Wu (b46) 2020; 193
Zeng, Yang, Xu, Zhou, Han (b42) 2019; 9
Li, Z., Zou, Y., Zhang, C., Zhang, Q., & Wei, Z. (2021). Learning Implicit Sentiment in Aspect-based Sentiment Analysis with Supervised Contrastive Pre-Training. In
Lv, Guo, Xu, Tang, Duan, Gong (b19) 2020; vol. 34
Wang, Zheng, Ye, Gan, Li, Song (b37) 2019
Mihaylov, T., & Frank, A. (2018). Knowledgeable Reader: Enhancing Cloze-Style Reading Comprehension with External Commonsense Knowledge. In
Poria (10.1016/j.ipm.2022.103223_b25) 2016; 108
10.1016/j.ipm.2022.103223_b11
Zhang (10.1016/j.ipm.2022.103223_b43) 2019
10.1016/j.ipm.2022.103223_b10
Schouten (10.1016/j.ipm.2022.103223_b27) 2015; 28
10.1016/j.ipm.2022.103223_b32
Vaswani (10.1016/j.ipm.2022.103223_b33) 2017
Lv (10.1016/j.ipm.2022.103223_b19) 2020; vol. 34
10.1016/j.ipm.2022.103223_b31
10.1016/j.ipm.2022.103223_b16
10.1016/j.ipm.2022.103223_b15
10.1016/j.ipm.2022.103223_b14
10.1016/j.ipm.2022.103223_b36
10.1016/j.ipm.2022.103223_b13
10.1016/j.ipm.2022.103223_b35
Zhang (10.1016/j.ipm.2022.103223_b45) 2020; 28
Gui (10.1016/j.ipm.2022.103223_b12) 2021
Zhao (10.1016/j.ipm.2022.103223_b47) 2019
Zhou (10.1016/j.ipm.2022.103223_b48) 2020; 1
10.1016/j.ipm.2022.103223_b18
Liang (10.1016/j.ipm.2022.103223_b17) 2022; 235
Song (10.1016/j.ipm.2022.103223_b30) 2019
Wu (10.1016/j.ipm.2022.103223_b39) 2020; 32
Wang (10.1016/j.ipm.2022.103223_b34) 2017; 29
Wang (10.1016/j.ipm.2022.103223_b37) 2019
Zeng (10.1016/j.ipm.2022.103223_b42) 2019; 9
10.1016/j.ipm.2022.103223_b41
10.1016/j.ipm.2022.103223_b40
10.1016/j.ipm.2022.103223_b23
10.1016/j.ipm.2022.103223_b22
10.1016/j.ipm.2022.103223_b44
Ferragina (10.1016/j.ipm.2022.103223_b9) 2011; 29
10.1016/j.ipm.2022.103223_b20
Sheu (10.1016/j.ipm.2022.103223_b29) 2021
10.1016/j.ipm.2022.103223_b26
10.1016/j.ipm.2022.103223_b24
Wu (10.1016/j.ipm.2022.103223_b38) 2019
10.1016/j.ipm.2022.103223_b28
10.1016/j.ipm.2022.103223_b1
10.1016/j.ipm.2022.103223_b3
Zhao (10.1016/j.ipm.2022.103223_b46) 2020; 193
10.1016/j.ipm.2022.103223_b2
10.1016/j.ipm.2022.103223_b5
10.1016/j.ipm.2022.103223_b4
10.1016/j.ipm.2022.103223_b7
10.1016/j.ipm.2022.103223_b6
10.1016/j.ipm.2022.103223_b8
Ma (10.1016/j.ipm.2022.103223_b21) 2021
References_xml – reference: (pp. 3433–3442).
– reference: (pp. 214–224).
– reference: Fan, F., Feng, Y., & Zhao, D. (2018). Multi-grained attention network for aspect-level sentiment classification. In
– reference: Phan, M. H., & Ogunbona, P. O. (2020). Modelling Context and Syntactical Features for Aspect-based Sentiment Analysis. In
– reference: Huang, B., & Carley, K. M. (2018). Parameterized Convolutional Neural Networks for Aspect Level Sentiment Classification. In
– reference: Xue, W., & Li, T. (2018). Aspect Based Sentiment Analysis with Gated Convolutional Networks. In
– reference: (pp. 3211–3220).
– reference: Ravichandran, D., & Hovy, E. (2002). Learning surface text patterns for a question answering system. In
– volume: 29
  start-page: 2724
  year: 2017
  end-page: 2743
  ident: b34
  article-title: Knowledge graph embedding: A survey of approaches and applications
  publication-title: IEEE Transactions on Knowledge and Data Engineering
– reference: (pp. 821–832).
– year: 2021
  ident: b29
  article-title: Knowledge-guided article embedding refinement for session-based news recommendation
  publication-title: IEEE Transactions on Neural Networks and Learning Systems
– reference: (pp. 1816–1829).
– volume: 32
  start-page: 4
  year: 2020
  end-page: 24
  ident: b39
  article-title: A comprehensive survey on graph neural networks
  publication-title: IEEE Transactions on Neural Networks and Learning Systems
– reference: (pp. 1121–1131).
– year: 2019
  ident: b30
  article-title: Attentional encoder network for targeted sentiment classification
– reference: (pp. 1145–1148).
– reference: Chollet, F. (2017). Xception: Deep learning with depthwise separable convolutions. In
– reference: (pp. 774–784).
– year: 2019
  ident: b47
  article-title: Muse: Parallel multi-scale attention for sequence to sequence learning
– reference: (pp. 41–47).
– volume: 28
  start-page: 813
  year: 2015
  end-page: 830
  ident: b27
  article-title: Survey on aspect-level sentiment analysis
  publication-title: IEEE Transactions on Knowledge and Data Engineering
– reference: Li, X., Bing, L., Lam, W., & Shi, B. (2018). Transformation Networks for Target-Oriented Sentiment Classification. In
– reference: Gao, T., Yao, X., & Chen, D. (2021). SimCSE: Simple Contrastive Learning of Sentence Embeddings. In
– volume: 193
  year: 2020
  ident: b46
  article-title: Modeling sentiment dependencies with graph convolutional networks for aspect-level sentiment classification
  publication-title: Knowledge-Based Systems
– reference: He, R., Lee, W. S., Ng, H. T., & Dahlmeier, D. (2018). Effective attention modeling for aspect-level sentiment classification. In
– reference: Tian, Y., Chen, G., & Song, Y. (2021). Aspect-based Sentiment Analysis with Type-aware Graph Convolutional Networks and Layer Ensemble. In
– reference: Ferragina, P., & Scaiella, U. (2010). Tagme: On-the-fly annotation of short text fragments (by Wikipedia entities). In
– volume: 9
  start-page: 3389
  year: 2019
  ident: b42
  article-title: Lcf: A local context focus mechanism for aspect-based sentiment classification
  publication-title: Applied Sciences
– reference: (pp. 1625–1628).
– reference: (pp. 4068–4074).
– reference: (pp. 2910–2922).
– reference: Wang, K., Shen, W., Yang, Y., Quan, X., & Wang, R. (2020). Relational Graph Attention Network for Aspect-based Sentiment Analysis. In
– reference: Devlin, J., Chang, M. W., Lee, K., & Toutanova, K. (2019). BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding. In
– reference: Wang, H., Zhang, F., Xie, X., & Guo, M. (2018). DKN: Deep knowledge-aware network for news recommendation. In
– reference: (pp. 1835–1844).
– reference: (pp. 901–904).
– reference: Shen, Y., Deng, Y., Yang, M., Li, Y., Du, N., Fan, W., et al. (2018). Knowledge-aware attentive neural network for ranking question answer pairs. In
– reference: Gu, S., Zhang, L., Hou, Y., & Song, Y. (2018). A position-aware bidirectional attention network for aspect-level sentiment analysis. In
– reference: (pp. 6894–6910).
– year: 2019
  ident: b37
  article-title: Deep graph library: A graph-centric, highly-performant package for graph neural networks
– reference: Zhang, C., Li, Q., & Song, D. (2019b). Syntax-aware aspect-level sentiment classification with proximity-weighted convolution network. In
– year: 2021
  ident: b12
  article-title: TextFlint: Unified multilingual robustness evaluation toolkit for natural language processing
– volume: 29
  start-page: 70
  year: 2011
  end-page: 75
  ident: b9
  article-title: Fast and accurate annotation of short texts with Wikipedia pages
  publication-title: IEEE Software
– reference: Dong, L., Wei, F., Zhou, M., & Xu, K. (2015). Question answering over freebase with multi-column convolutional neural networks. In
– reference: Lin, Y., Liu, Z., Sun, M., Liu, Y., & Zhu, X. (2015). Learning entity and relation embeddings for knowledge graph completion. In
– volume: 108
  start-page: 42
  year: 2016
  end-page: 49
  ident: b25
  article-title: Aspect extraction for opinion mining with a deep convolutional neural network
  publication-title: Knowledge-Based Systems
– reference: (pp. 3229–3238).
– volume: 1
  start-page: 57
  year: 2020
  end-page: 81
  ident: b48
  article-title: Graph neural networks: A review of methods and applications
  publication-title: AI Open
– reference: (pp. 946–956).
– start-page: 4568
  year: 2019
  end-page: 4578
  ident: b43
  article-title: Aspect-based sentiment classification with aspect-specific graph convolutional networks
  publication-title: Proceedings of the 2019 conference on empirical methods in natural language processing and the 9th international joint conference on natural language processing
– volume: 28
  start-page: 2538
  year: 2020
  end-page: 2551
  ident: b45
  article-title: Knowledge guided capsule attention network for aspect-based sentiment analysis
  publication-title: IEEE/ACM Transactions on Audio, Speech, and Language Processing
– reference: Ma, D., Li, S., Zhang, X., & Wang, H. (2017). Interactive attention networks for aspect-level sentiment classification. In
– reference: (pp. 3594–3605).
– reference: (pp. 260–269).
– reference: (pp. 1091–1096).
– reference: Pontiki, M., Galanis, D., Papageorgiou, H., Androutsopoulos, I., Manandhar, S., Al-Smadi, M., et al. (2016). Semeval-2016 task 5: Aspect based sentiment analysis. In
– reference: (pp. 293–296).
– reference: (pp. 4171–4186).
– reference: Davidson, J., Liebald, B., Liu, J., Nandy, P., Van Vleet, T., Gargi, U., et al. (2010). The YouTube video recommendation system. In
– reference: Mihaylov, T., & Frank, A. (2018). Knowledgeable Reader: Enhancing Cloze-Style Reading Comprehension with External Commonsense Knowledge. In
– volume: 235
  start-page: 107643
  year: 2022
  ident: b17
  article-title: Aspect-based sentiment analysis via affective knowledge enhanced graph convolutional networks
  publication-title: Knowl.-Based Syst.
– reference: Tang, D., Qin, B., & Liu, T. (2016). Aspect Level Sentiment Classification with Deep Memory Network. In
– reference: Dai, J., Yan, H., Sun, T., Liu, P., & Qiu, X. (2021). Does syntax matter? A strong baseline for Aspect-based Sentiment Analysis with RoBERTa. In
– reference: .
– reference: (pp. 2514–2523).
– reference: Li, Z., Zou, Y., Zhang, C., Zhang, Q., & Wei, Z. (2021). Learning Implicit Sentiment in Aspect-based Sentiment Analysis with Supervised Contrastive Pre-Training. In
– reference: (pp. 19–30).
– reference: Xing, X., Jin, Z., Jin, D., Wang, B., Zhang, Q., & Huang, X. J. (2020). Tasty Burgers, Soggy Fries: Probing Aspect Robustness in Aspect-Based Sentiment Analysis. In
– reference: (pp. 1251–1258).
– year: 2021
  ident: b21
  article-title: Exploiting position bias for robust aspect sentiment classification
– reference: (pp. 246–256).
– reference: Bahdanau, D., Cho, K. H., & Bengio, Y. (2015). Neural machine translation by jointly learning to align and translate. In
– volume: vol. 34
  start-page: 8449
  year: 2020
  end-page: 8456
  ident: b19
  article-title: Graph-based reasoning over heterogeneous external knowledge for commonsense question answering
  publication-title: Proceedings of the AAAI conference on artificial intelligence
– start-page: 5998
  year: 2017
  end-page: 6008
  ident: b33
  article-title: Attention is all you need
  publication-title: Advances in neural information processing systems
– year: 2019
  ident: b38
  article-title: Pay less attention with lightweight and dynamic convolutions
– ident: 10.1016/j.ipm.2022.103223_b10
  doi: 10.18653/v1/2021.emnlp-main.552
– start-page: 5998
  year: 2017
  ident: 10.1016/j.ipm.2022.103223_b33
  article-title: Attention is all you need
– volume: 1
  start-page: 57
  year: 2020
  ident: 10.1016/j.ipm.2022.103223_b48
  article-title: Graph neural networks: A review of methods and applications
  publication-title: AI Open
  doi: 10.1016/j.aiopen.2021.01.001
– ident: 10.1016/j.ipm.2022.103223_b15
  doi: 10.18653/v1/P18-1087
– ident: 10.1016/j.ipm.2022.103223_b24
  doi: 10.18653/v1/S16-1002
– volume: 32
  start-page: 4
  issue: 1
  year: 2020
  ident: 10.1016/j.ipm.2022.103223_b39
  article-title: A comprehensive survey on graph neural networks
  publication-title: IEEE Transactions on Neural Networks and Learning Systems
  doi: 10.1109/TNNLS.2020.2978386
– ident: 10.1016/j.ipm.2022.103223_b18
  doi: 10.1609/aaai.v29i1.9491
– ident: 10.1016/j.ipm.2022.103223_b32
  doi: 10.18653/v1/2021.naacl-main.231
– ident: 10.1016/j.ipm.2022.103223_b2
  doi: 10.1109/CVPR.2017.195
– volume: 29
  start-page: 70
  issue: 1
  year: 2011
  ident: 10.1016/j.ipm.2022.103223_b9
  article-title: Fast and accurate annotation of short texts with Wikipedia pages
  publication-title: IEEE Software
  doi: 10.1109/MS.2011.122
– year: 2021
  ident: 10.1016/j.ipm.2022.103223_b21
– ident: 10.1016/j.ipm.2022.103223_b35
  doi: 10.18653/v1/2020.acl-main.295
– volume: 29
  start-page: 2724
  issue: 12
  year: 2017
  ident: 10.1016/j.ipm.2022.103223_b34
  article-title: Knowledge graph embedding: A survey of approaches and applications
  publication-title: IEEE Transactions on Knowledge and Data Engineering
  doi: 10.1109/TKDE.2017.2754499
– ident: 10.1016/j.ipm.2022.103223_b26
  doi: 10.3115/1073083.1073092
– start-page: 4568
  year: 2019
  ident: 10.1016/j.ipm.2022.103223_b43
  article-title: Aspect-based sentiment classification with aspect-specific graph convolutional networks
– ident: 10.1016/j.ipm.2022.103223_b16
  doi: 10.18653/v1/2021.emnlp-main.22
– ident: 10.1016/j.ipm.2022.103223_b44
  doi: 10.1145/3331184.3331351
– year: 2019
  ident: 10.1016/j.ipm.2022.103223_b38
– year: 2021
  ident: 10.1016/j.ipm.2022.103223_b12
– ident: 10.1016/j.ipm.2022.103223_b40
  doi: 10.18653/v1/2020.emnlp-main.292
– ident: 10.1016/j.ipm.2022.103223_b22
  doi: 10.18653/v1/P18-1076
– volume: 108
  start-page: 42
  year: 2016
  ident: 10.1016/j.ipm.2022.103223_b25
  article-title: Aspect extraction for opinion mining with a deep convolutional neural network
  publication-title: Knowledge-Based Systems
  doi: 10.1016/j.knosys.2016.06.009
– volume: 235
  start-page: 107643
  year: 2022
  ident: 10.1016/j.ipm.2022.103223_b17
  article-title: Aspect-based sentiment analysis via affective knowledge enhanced graph convolutional networks
  publication-title: Knowl.-Based Syst.
  doi: 10.1016/j.knosys.2021.107643
– volume: vol. 34
  start-page: 8449
  year: 2020
  ident: 10.1016/j.ipm.2022.103223_b19
  article-title: Graph-based reasoning over heterogeneous external knowledge for commonsense question answering
– year: 2019
  ident: 10.1016/j.ipm.2022.103223_b47
– ident: 10.1016/j.ipm.2022.103223_b3
  doi: 10.18653/v1/2021.naacl-main.146
– volume: 28
  start-page: 813
  issue: 3
  year: 2015
  ident: 10.1016/j.ipm.2022.103223_b27
  article-title: Survey on aspect-level sentiment analysis
  publication-title: IEEE Transactions on Knowledge and Data Engineering
  doi: 10.1109/TKDE.2015.2485209
– ident: 10.1016/j.ipm.2022.103223_b5
– ident: 10.1016/j.ipm.2022.103223_b36
  doi: 10.1145/3178876.3186175
– volume: 193
  year: 2020
  ident: 10.1016/j.ipm.2022.103223_b46
  article-title: Modeling sentiment dependencies with graph convolutional networks for aspect-level sentiment classification
  publication-title: Knowledge-Based Systems
  doi: 10.1016/j.knosys.2019.105443
– ident: 10.1016/j.ipm.2022.103223_b14
  doi: 10.18653/v1/D18-1136
– ident: 10.1016/j.ipm.2022.103223_b1
– ident: 10.1016/j.ipm.2022.103223_b23
  doi: 10.18653/v1/2020.acl-main.293
– year: 2021
  ident: 10.1016/j.ipm.2022.103223_b29
  article-title: Knowledge-guided article embedding refinement for session-based news recommendation
  publication-title: IEEE Transactions on Neural Networks and Learning Systems
– ident: 10.1016/j.ipm.2022.103223_b6
  doi: 10.3115/v1/P15-1026
– ident: 10.1016/j.ipm.2022.103223_b7
  doi: 10.18653/v1/D18-1380
– year: 2019
  ident: 10.1016/j.ipm.2022.103223_b30
– ident: 10.1016/j.ipm.2022.103223_b31
  doi: 10.18653/v1/D16-1021
– ident: 10.1016/j.ipm.2022.103223_b8
  doi: 10.1145/1871437.1871689
– year: 2019
  ident: 10.1016/j.ipm.2022.103223_b37
– ident: 10.1016/j.ipm.2022.103223_b11
– volume: 28
  start-page: 2538
  year: 2020
  ident: 10.1016/j.ipm.2022.103223_b45
  article-title: Knowledge guided capsule attention network for aspect-based sentiment analysis
  publication-title: IEEE/ACM Transactions on Audio, Speech, and Language Processing
  doi: 10.1109/TASLP.2020.3017093
– ident: 10.1016/j.ipm.2022.103223_b4
  doi: 10.1145/1864708.1864770
– ident: 10.1016/j.ipm.2022.103223_b20
  doi: 10.24963/ijcai.2017/568
– ident: 10.1016/j.ipm.2022.103223_b41
  doi: 10.18653/v1/P18-1234
– volume: 9
  start-page: 3389
  issue: 16
  year: 2019
  ident: 10.1016/j.ipm.2022.103223_b42
  article-title: Lcf: A local context focus mechanism for aspect-based sentiment classification
  publication-title: Applied Sciences
  doi: 10.3390/app9163389
– ident: 10.1016/j.ipm.2022.103223_b13
– ident: 10.1016/j.ipm.2022.103223_b28
  doi: 10.1145/3209978.3210081
SSID ssj0004512
Score 2.5889125
Snippet Aspect-based sentiment analysis aims to determine sentiment polarities toward specific aspect terms within the same sentence or document. Most recent studies...
SourceID crossref
elsevier
SourceType Enrichment Source
Index Database
Publisher
StartPage 103223
SubjectTerms Attention mechanism
Conceptual knowledge
Graph neural network
Robustness analysis
Sentiment analysis
Title Knowledge-guided multi-granularity GCN for ABSA
URI https://dx.doi.org/10.1016/j.ipm.2022.103223
Volume 60
WOSCitedRecordID wos000961166400001&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText 1
inHoldings 1
isFullTextHit
isPrint
journalDatabaseRights – providerCode: PRVESC
  databaseName: Elsevier SD Freedom Collection Journals 2021
  customDbUrl:
  eissn: 1873-5371
  dateEnd: 99991231
  omitProxy: false
  ssIdentifier: ssj0004512
  issn: 0306-4573
  databaseCode: AIEXJ
  dateStart: 19950101
  isFulltext: true
  titleUrlDefault: https://www.sciencedirect.com
  providerName: Elsevier
link http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwtV3JTsMwELXYDlwQqyibfEAckFKK48TJsexQVCEBUsUlShy7i1CouqDy94xjp01biuiBS1pZGafNPI2fx7MgdMyYzUJxHlox4cSiceRaYRRx2KpIWwI_gjU4rTP7yKpVr1bzn0wKQTdtJ8CSxBsM_Pa_qhrGQNkqdXYOdQ8nhQH4DkqHK6gdrn9SfCXzkln1fjMGPpnGDFp1WJRUyKli3beX1TS8sHzxXM6zU5OblEKirTMItCfBNVGu-TCZt0Y_PdloiESGZv3Le6CvAHhf_VzIT9P4AMYHKkIKI22cD8QeRV9lSVcl16KO7kaSGVTdIMAAh-Ssoyrep7OLpwy39iG0is22Kg9ASHF073iR7InFaxhSmEWrtQKYIlBTBHqKRbRMmOODxVsu31_XHnK15M_NGZP-C9mZdxr9N_E7fmYtOSbyso7WzBYCl7XqN9CCSDbRoUlAwSc4p0VsTPcWOpuEBZ6CBQZYYBDFChbb6PXm-uXyzjLNMixOfNZTq5qntu8sJiTyY096IVBd23ZcHtuey6mvKk0xL1IF22wKH1JSRoRDQhgDKrODlpKPROwiTENOqR9KoG6COr4XxbZboiASSw6U0C2gUvYyAm4qyauGJu_BTCUU0OlQpK3LqPx2M83ecGB4oOZ3AaBlttjePM_YR6sjPB-gpV6nLw7RCv_sNbudIwOVb68cd7I
linkProvider Elsevier
openUrl ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Knowledge-guided+multi-granularity+GCN+for+ABSA&rft.jtitle=Information+processing+%26+management&rft.au=Zhu%2C+Zhenfang&rft.au=Zhang%2C+Dianyuan&rft.au=Li%2C+Lin&rft.au=Li%2C+Kefeng&rft.date=2023-03-01&rft.issn=0306-4573&rft.volume=60&rft.issue=2&rft.spage=103223&rft_id=info:doi/10.1016%2Fj.ipm.2022.103223&rft.externalDBID=n%2Fa&rft.externalDocID=10_1016_j_ipm_2022_103223
thumbnail_l http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0306-4573&client=summon
thumbnail_m http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0306-4573&client=summon
thumbnail_s http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0306-4573&client=summon