Attention-based LSTM for Aspect-level Sentiment Classification
Open accessThe DOI matches its Crossref record; 39 of the 39 references it cites were found in a registry or an index.
Abstract
Aspect-level sentiment classification is a finegrained task in sentiment analysis.Since it provides more complete and in-depth results, aspect-level sentiment analysis has received much attention these years.In this paper, we reveal that the sentiment polarity of a sentence is not only determined by the content but is also highly related to the concerned aspect.For instance, "The appetizers are ok, but the service is slow.",for aspect taste, the polarity is positive while for service, the polarity is negative.Therefore, it is worthwhile to explore the connection between an aspect and the content of a sentence.To this end, we propose an Attention-based Long Short-Term Memory Network for aspect-level sentiment classification.The attention mechanism can concentrate on different parts of a sentence when different aspects are taken as input.We experiment on the SemEval 2014 dataset and results show that our model achieves state-ofthe-art performance on aspect-level sentiment classification.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The cited source says what the claim attributes to it.
In the citing paper
“While these methods are widely adopted [24, 43, 49, 75], alternative approaches may provide more benefit to team performance.”
From Does the Whole Exceed its Parts? The Effect of AI Explanations on Complementary Team Performance (2021) · cites this paper as [75]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Hochreiter, S., & Schmidhuber, J. (1997) · Neural Computation · doi:10.1162/neco.1997.9.8.1735 · Cited by 102,318 · cited 3×
“…et al., 2011; Dong et al., 2014; Qian et al., 2015), Recursive Neural Tensor Network (Socher et al., 2013), Recurrent Neural Network (Mikolov et al., 2010; Tang et al., 2015b), LSTM (Hochreiter and Schmidhuber, 1997) and Tree-LSTMs (Tai et al., 2015) were applied into sentiment analysis currently.”
BackgroundMethodGlove: Global Vectors for Word Representation
Pennington, J., Socher, R., & Manning, C. (2014) · Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.3115/v1/d14-1162 · Cited by 34,071 · cited 1×
“In our experiments, all word vectors are initialized by Glove1 (Pennington et al., 2014).”
MethodDistributed Representations of Words and Phrases and their Compositionality
Mikolov, T., Sutskever, I., Chen, K., Corrado, G., & Dean, J. (2013) · arXiv · doi:10.48550/arxiv.1310.4546 · Cited by 24,533
Neural Machine Translation by Jointly Learning to Align and Translate
Bahdanau, D., Cho, K., & Bengio, Y. (2014) · arXiv · doi:10.48550/arxiv.1409.0473 · Cited by 16,213 · cited 2×
“Attention has become an effective mechanism to obtain superior results, as demonstrated in image recognition (Mnih et al., 2014), machine translation (Bahdanau et al., 2014), reasoning about entailment (Rockt¨aschel et al., 2015) and sentence summarization (Rush et al., 2015).”
Background(2010) · Cited by 8,261
Recursive Deep Models for Semantic Compositionality Over a Sentiment Treebank
Socher, R., Perelygin, A., Wu, J., Chuang, J., Manning, C. D., Ng, A., & Potts, C. (2013) · Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d13-1170 · Cited by 6,878 · cited 3×
“, 2015), Recursive Neural Tensor Network (Socher et al., 2013), Recurrent Neural Network (Mikolov et al.”
BackgroundMethodRecurrent neural network based language model
Mikolov, T., Karafiát, M., Burget, L., Černocký, J., & Khudanpur, S. (2010) · Interspeech 2010 · doi:10.21437/interspeech.2010-343 · Cited by 5,390
Large Scale Distributed Deep Networks
Dean, J. B., Corrado, G. S., Monga, R., Chen, K., Devin, M., Mao, M., Ranzato, M., Senior, A., Tucker, P. A., Yang, K., et al. (2012) · neural information processing systems · Cited by 4,489
Neural Architectures for Named Entity Recognition
Lample, G., Ballesteros, M., Subramanian, S., Kawakami, K., & Dyer, C. (2016) · Proceedings of the 2016 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies · doi:10.18653/v1/n16-1030 · Cited by 4,401 · cited 2×
“Neural networks have achieved state-of-the-art performance in a variety of NLP tasks such as machine translation (Lample et al., 2016), paraphrase identification (Yin et al., 2015), question answering (Golub and He, 2016) and text summarization (Rush et al., 2015).”
BackgroundSentiment Analysis and Opinion Mining
Liu, B. (2012) · Synthesis Lectures on Human Language Technologies · doi:10.1007/978-3-031-02145-9 · Cited by 3,281 · cited 1×
“Sentiment analysis (Nasukawa and Yi, 2003), also known as opinion mining (Liu, 2012), is a key NLP task that receives much attention these years.”
Background
Research works printed but not linked: 1
- Tomas Mikolov, Ilya Sutskever, Kai Chen, Greg S Cor- rado, and Jeff Dean. 2013. Distributed representa- tions of words and phrases and their compositional- ity. In Advances in Neural Information Processing Systems, pages 3111-3119.
Cited by
Items 101–200 of 1,003
Learning to Attend via Word-Aspect Associative Fusion for Aspect-Based Sentiment Analysis
Tay, Y., Tuan, L. A., & Hui, S. C. (2018) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v32i1.12049 · Cited by 193
Does syntax matter? A strong baseline for Aspect-based Sentiment Analysis with RoBERTa
Dai, J., Yan, H., Sun, T., Liu, P., & Qiu, X. (2021) · Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies · doi:10.18653/v1/2021.naacl-main.146 · Cited by 163
Sentiment analysis using deep learning approaches: an overview
Habimana, O., Li, Y., Li, R., Gu, X., & Yu, G. (2020) · Science China Information Sciences · doi:10.1007/s11432-018-9941-6 · Cited by 186
Weakly Supervised Framework for Aspect-Based Sentiment Analysis on Students’ Reviews of MOOCs
Kastrati, Z., Imran, A. S., & Kurti, A. (2020) · IEEE Access · doi:10.1109/access.2020.3000739 · Cited by 173
“[34] stated that ‘‘the”
TextConvoNet: a convolutional neural network based architecture for text classification
Soni, S., Chouhan, S. S., & Rathore, S. S. (2023) · Applied Intelligence · doi:10.1007/s10489-022-04221-9 · Cited by 176
“It is because of the exponential function and normalized alignment score computation of all the words in the text [21].”
BackgroundNaseem, U., Razzak, I., Khan, S. K., & Prasad, M. (2021) · ACM Transactions on Asian and Low-Resource Language Information Processing · doi:10.1145/3434237 · Cited by 194
“Similarly, a study conducted by Wang et al. [166], used pre-trained GloVe embeddings as an input to LSTM with attention model for aspect based classification and Liu et al. [85] employed pre-trained word embeddings Word2Vec for recommending idioms in essay writing.”
MethodAn improved aspect-category sentiment analysis model for text sentiment analysis based on RoBERTa
Liao, W., Zeng, B., Yin, X., & Wei, P. (2021) · Applied Intelligence · doi:10.1007/s10489-020-01964-1 · Cited by 180
“To focus on the span of text more relevant to the given aspect, many works [7, 21, 22] combine the LSTM with the attention mechanism.”
BackgroundMethodInfluentialApplications of Long Short-Term Memory (LSTM) Networks in Polymeric Sciences: A Review
Malashin, I. P., Тынченко, В. С., Gantimurov, A., Nelyub, V., & Бородулин, А. С. (2024) · Polymers · doi:10.3390/polym16182607 · Cited by 214
“Finally, Attention-Based LSTM [45] incorporates an attention mechanism, allowing the model to focus on important parts of the sequence when making predictions.”
MethodTarget-Aspect-Sentiment Joint Detection for Aspect-Based Sentiment Analysis
Wan, H., Yang, Y., Du, J., Liu, Y., Qi, K., & Pan, J. Z. (2020) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v34i05.6447 · Cited by 171
“…there are two simpler tasks for ABSA, where one aims to classify the sentiment according to a given aspect, which has been investigated e.g. in (Wang et al. 2016; Xue and Li 2018), and the other aims to classify the sentiment according to a given target, studied e.g. in (Zeng, Ma, and Zhou…”
MethodResultAspect-based sentiment analysis with alternating coattention networks
Yang, C., Zhang, H., Jiang, B., & Li, K. (2019) · Information Processing & Management · doi:10.1016/j.ipm.2018.12.004 · Cited by 179
“Sentiment classifier Similar to other models (Chen et al., 2017; Ma et al., 2017; Tang et al., 2016b; Tay et al., 2018; Wang et al., 2016), we use a softmax layer as the sentiment classifier.”
MethodWeakly-Supervised Deep Embedding for Product Review Sentiment Analysis
Zhao, W., Guan, Z., Chen, L., He, X., Cai, D., Wang, B., & Wang, Q. (2018) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2017.2756658 · Cited by 177
“[49] introduced the attentionmechanism into LSTM to learn aspect specific sentence representation.”
BackgroundTarget-Sensitive Memory Networks for Aspect Sentiment Classification
Wang, S., Mazumder, S., Liu, B., Zhou, M., & Chang, Y. (2018) · Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/p18-1088 · Cited by 179
“Another common neural model using attention mechanism is the RNN/LSTM (Wang et al., 2016).”
BackgroundMethodResultInfluentialPeng, H., Li, J., Wang, S., Wang, L., Gong, Q., Yang, R., Li, B., Yu, P. S., & He, L. (2021) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2019.2959991 · Cited by 176
“Recent advances in deep learning techniques [2], [3] have enabled numerous variants of neural network based models from a large body of innovations, encompassing recurrent neural networks [4], [5], [6], [7], diversified convolutional neural networks [8], [9], [10], [11], [12], [13], capsule neural networks [14] and ad…”
BackgroundElf: accelerate high-resolution mobile deep vision with content-aware parallel offloading
Zhang, W., He, Z., Liu, L., Jia, Z., Liu, Y., Gruteser, M., Raychaudhuri, D., & Zhang, Y. (2021) · Proceedings of the 27th Annual International Conference on Mobile Computing and Networking · doi:10.1145/3447993.3448628 · Cited by 172
Stance Classification with Target-specific Neural Attention
Du, J., Xu, R., He, Y., & Gui, L. (2017) · International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2017/557 · Cited by 274
Multi-level convolutional autoencoder networks for parametric prediction of spatio-temporal dynamics
Xu, J., & Duraisamy, K. (2020) · Computer Methods in Applied Mechanics and Engineering · doi:10.1016/j.cma.2020.113379 · Cited by 171
Yang, H., Zeng, B., Yang, J., Song, Y., & Xu, R. (2021) · Neurocomputing · doi:10.1016/j.neucom.2020.08.001 · Cited by 164
Mutinda, J., Mwangi, W. R., & Okeyo, G. O. (2023) · Applied Sciences · doi:10.3390/app13031445 · Cited by 198
“Wang et al. [35] used pre-trained Glove vectors as inputs for attention-based LSTM models for aspect-level sentiment analysis.”
Twitter Sentiment Analysis via Bi-sense Emoji Embedding and Attention-based LSTM
Chen, Y., Yuan, J., You, Q., & Luo, J. (2018) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3240508.3240533 · Cited by 190
“, as shown in Equation 5: αi = exp(fatt(ei,h)) ˝ m i=1 exp(fatt(ei,h)) v′= Õm i=1 (αi ·ei) (5) The derived senti-emoji embedding v′is then used to calculate an additional layer of attention following [9, 42]. Given the input tweet sequence {w1,w2,...,wT }, the attention weight α′t,t ∈(1,T) conditioned on the senti-emo…”
BackgroundMethodCode smell detection by deep direct-learning and transfer-learning
Sharma, T., Efstathiou, V., Λουρίδας, Π., & Spinellis, D. D. (2021) · Journal of Systems and Software · doi:10.1016/j.jss.2021.110936 · Cited by 186
“In addition, they have been established as state-of-the-art networks for a variety of natural language processing tasks; indicative applications include natural language generation [97], sentiment classification [7, 95] and neural machine translation [11], among others.”
BackgroundDOER: Dual Cross-Shared RNN for Aspect Term-Polarity Co-Extraction
Luo, H., Li, T., Liu, B., & Zhang, J. (2019) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/p19-1056 · Cited by 181
“Convolution neural networks (CNNs) (Poria et al., 2016; Li and Xue, 2018), attention network (Wang et al., 2016b; Ma et al., 2017; He et al., 2017), and memory network (Wang et al., 2018) are also active approaches.”
BackgroundZhang, Z., Zhou, Z., & Wang, Y. (2022) · Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT) · doi:10.18653/v1/2022.naacl-main.362 · Cited by 236
“…solve aspect-based sentiment analysis by utilizing attention-based neural network to model semantic correlation between context and aspect term (Wang et al., 2016; Chen et al., 2017; Ma et al., 2017; Liu et al., 2018; Hu et al., 2018; Wang et al., 2018; Huang et al., 2018; Fan et al., 2018).”
BackgroundMethodInfluentialSelf-citationZhong, Q., Ding, L., Liu, J., Du, B., Jin, H., & Tao, D. (2023) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2023.3250499 · Cited by 196
A survey on aspect-based sentiment classification
Brauwers, G., & Frasincar, F. (2023) · ACM Computing Surveys · doi:10.1145/3503044 · Cited by 165
“One of the most common score functions is the additive score function [15], which is used in many ABSC models [210]:”
MethodCoevolutionary Recommendation Model: Mutual Learning between Ratings and Reviews
Lu, Y., Dong, R., & Smyth, B. (2018) · International World Wide Web Conference (WWW) · doi:10.1145/3178876.3186158 · Cited by 187
“RNNs are commonly used to capture or summarize the meaning of sentences or documents in various tasks such as machine translation[2], sentence summarization [32] and sentiment analysis [38, 42].”
MethodEffective Attention Modeling for Aspect-Level Sentiment Classification
He, R., Lee, W. S., Ng, H. T., & Dahlmeier, D. (2018) · International Conference on Computational Linguistics · Cited by 234
VGCN-BERT: Augmenting BERT with Graph Embedding for Text Classification
Lu, Z., Du, P., & Nie, J. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-45439-5_25 · Cited by 203
“As aforementioned, attention mechanisms [31,28] based on various deep neural networks, in particular the self-attention mechanism proposed by Vaswan et al.”
BackgroundLearning multi-grained aspect target sequence for Chinese sentiment analysis
Peng, H., Ma, Y., Li, Y., & Cambria, E. (2018) · Knowledge-Based Systems · doi:10.1016/j.knosys.2018.02.034 · Cited by 160
Neural Machine Reading Comprehension: Methods and Trends
Liu, S., Zhang, X., Zhang, S., Wang, H., & Zhang, W. (2019) · Applied Sciences · doi:10.3390/app9183698 · Cited by 158
Adversarial Training for Aspect-Based Sentiment Analysis with BERT
Karimi, A., Rossi, L., & Prati, A. (2021) · 2020 25th International Conference on Pattern Recognition (ICPR) · doi:10.1109/icpr48806.2021.9412167 · Cited by 138
“the abundance of available data and computational power, deep learning methods such as Convolutional Neural Nets (CNNs) [7], [8], [9], Recurrent Neural Networks (RNNs) [10], [11], [12], and the Transformer [13] have outperformed the traditional machine learning techniques in various tasks”
MethodCLMLF:A Contrastive Learning and Multi-Layer Fusion Method for Multimodal Sentiment Detection
Li, Z., Xu, B. H., Zhu, C., & Zhao, T. (2022) · Findings of the Association for Computational Linguistics: NAACL · doi:10.18653/v1/2022.findings-naacl.175 · Cited by 217
Deep Learning for Aspect-Level Sentiment Classification: Survey, Vision, and Challenges
Zhou, J., Huang, J. X., Chen, Q., Hu, Q., Wang, T., & He, L. (2019) · IEEE Access · doi:10.1109/access.2019.2920075 · Cited by 175
“[29] proposed an attention-based LSTM method with aspect embedding, which was proven to be an effective way to enforce the model to capture the related parts of a sentence.”
BackgroundMethodInfluentialBiLSTM with Multi-Polarity Orthogonal Attention for Implicit Sentiment Analysis
Wei, J., Liao, J., Yang, Z., Wang, S., & Zhao, Q. (2020) · Neurocomputing · doi:10.1016/j.neucom.2019.11.054 · Cited by 159
Song, M., Park, H., & Shin, K.-S. (2019) · Information Processing & Management · doi:10.1016/j.ipm.2018.12.005 · Cited by 163
Hierarchical Interactive Multimodal Transformer for Aspect-Based Multimodal Sentiment Analysis
Yu, J., Chen, K., & Xia, R. (2022) · IEEE Transactions on Affective Computing · doi:10.1109/taffc.2022.3171091 · Cited by 177
“AE-LSTM [7]: an attention-based LSTM model which integrates aspect embedding into the sentence input.”
BackgroundMethodInfluentialDashtipour, K. K., Gogate, M., Li, J., Jiang, F., Kong, B., & Hussain, A. (2019) · Neurocomputing · doi:10.1016/j.neucom.2019.10.009 · Cited by 165
Topic-level sentiment analysis of social media data using deep learning
Pathak, A. R., Pandey, M., & Rautaray, S. S. (2021) · Applied Soft Computing · doi:10.1016/j.asoc.2021.107440 · Cited by 164
Aspect-Based Opinion Mining on Student’s Feedback for Faculty Teaching Performance Evaluation
Sindhu, I., Daudpota, S. M., Badar, K., Bakhtyar, M., Baber, J., & Nurunnabi, M. (2019) · IEEE Access · doi:10.1109/access.2019.2928872 · Cited by 150
“In [21] target dependent LSTM and its variant target connection LSTM was proposed.”
BackgroundA Review of Text Corpus-Based Tourism Big Data Mining
Li, Q., Li, S., Zhang, S., Hu, J., & Hu, J. (2019) · Applied Sciences · doi:10.3390/app9163300 · Cited by 160
“76.01 ATAE-LSTM [113] On the basis of TD-LSTM, aspect information is introduced in two parts of the model: Input part and hidden part 77.20 IAN [116] It learns attentions in target and context words interactively, and generates the representations for targets and contexts separately.”
InfluentialLi, Z., Zou, Y., Zhang, C., Zhang, Q., & Wei, Z. (2021) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2021.emnlp-main.22 · Cited by 177
“Recent studies tackle the task by either employing attention mechanisms (Wang et al., 2016b; Ma et al., 2017) or incorporating syntax-aware graph structures (He et al.”
InfluentialAspect-level Sentiment Classification with HEAT (HiErarchical ATtention) Network
Cheng, J., Zhao, S., Zhang, J., King, I., Zhang, X., & Wang, H. (2017) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3132847.3133037 · Cited by 153
“ATAE-LSTM has achieved the state-of-the-art performance on REST14.”
BackgroundMethodResultInfluentialA deep learning method based on an attention mechanism for wireless network traffic prediction
Li, M., Wang, Y., Wang, Z., & Zheng, H. (2020) · Ad Hoc Networks · doi:10.1016/j.adhoc.2020.102258 · Cited by 141
Self-citationA Position-aware Bidirectional Attention Network for Aspect-level Sentiment Analysis
Gu, S., Zhang, L., Hou, Y., & Song, Y. (2018) · International Conference on Computational Linguistics · Cited by 139
Irony detection via sentiment-based transfer learning
Zhang, S., Zhang, X., Chan, J., & Rosso, P. (2019) · Information Processing & Management · doi:10.1016/j.ipm.2019.04.006 · Cited by 156
Arabic aspect based sentiment analysis using bidirectional GRU based models
Abdelgwad, M. M., Soliman, T. H. A., Taloba, A. I., & Farghaly, M. F. (2021) · Journal of King Saud University - Computer and Information Sciences · doi:10.1016/j.jksuci.2021.08.030 · Cited by 160
“For each word embedding, ATAE-LSTM adds aspects embedding that reinforce the model by learning the hidden association between context and aspect (Wang et al., 2016).”
InfluentialDAE-GAN: Dynamic Aspect-aware GAN for Text-to-Image Synthesis
Ruan, S., Zhang, Y., Zhang, K., Fan, Y., Tang, F., Liu, Q., & Chen, E. (2021) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.01370 · Cited by 171
“Semantic understanding of a sentence is highly dependent on both content and aspect[33].”
BackgroundSentiment Analysis of Text Based on Bidirectional LSTM With Multi-Head Attention
Long, F., Zhou, K., & Ou, W. (2019) · IEEE Access · doi:10.1109/access.2019.2942614 · Cited by 149
“In addition, considering that text sentiment analysis is fundamentally a sequence problem, this paper combines a multi-head attention mechanism with the BiLSTM into a hybrid model for text sentiment analysis [18].”
MethodLearning Fragment Self-Attention Embeddings for Image-Text Matching
Wu, Y., Wang, S., Song, G., & Huang, Q. (2019) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3343031.3350940 · Cited by 160
“The textual attention approaches also benefit sentiment classification [41], neural machine translation [21, 36], sentence summarization [33], etc.”
BackgroundAn algorithm and method for sentiment analysis using the text and emoticon
Ullah, M. A., Marium, S. M., Begum, S. A., & Dipa, N. S. (2020) · ICT Express · doi:10.1016/j.icte.2020.07.003 · Cited by 133
Aspect-based sentiment classification with multi-attention network
Xu, Q., Zhu, L., Dai, T., & Yan, C. (2020) · Neurocomputing · doi:10.1016/j.neucom.2020.01.024 · Cited by 130
Privacy-preserving Neural Representations of Text
Coavoux, M., Narayan, S., & Cohen, S. B. (2018) · Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d18-1001 · Cited by 94
“LSTM-based architectures have been applied to many NLP tasks, including sentiment classification (Wang et al., 2016) and text classification (Zhou et al.”
MethodIARM: Inter-Aspect Relation Modeling with Memory Networks in Aspect-Based Sentiment Analysis
Majumder, N., Poria, S., Gelbukh, A., Akhtar, M. S., Cambria, E., & Ekbal, A. (2018) · Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d18-1377 · Cited by 126
“This leads to two tasks to be solved: aspect extraction (Shu et al., 2017) and aspect sentiment polarity detection (Wang et al., 2016).”
BackgroundMethodInfluentialZhang, K. F., Cao, H., Thé, J. V. G., & Yu, H. (2021) · Applied Energy · doi:10.1016/j.apenergy.2021.118011 · Cited by 129
Liang, B., Yin, R., Gui, L., Du, J., & Xu, R. (2020) · International Conference on Computational Linguistics · doi:10.18653/v1/2020.coling-main.13 · Cited by 141
“TD-LSTM (Tang et al., 2016a) models bidirectional contextual features for a given aspect with LSTMs. ATAE-LSTM (Wang et al., 2016b) explores aspect-specific attention mechanism based on LSTM. MemNet (Tang et al., 2016b) exploits word and position attention to focus on specific aspect by a multi-hop memory network.”
BackgroundMethodInfluentialLearning multiple layers of knowledge representation for aspect based sentiment analysis
Pham, D.-H., & Le, A.-C. (2017) · Data & Knowledge Engineering · doi:10.1016/j.datak.2017.06.001 · Cited by 132
Interactive Attention Transfer Network for Cross-Domain Sentiment Classification
Zhang, K., Zhang, H., Liu, Q., Zhao, H., Zhu, H., & Chen, E. (2019) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v33i01.33015773 · Cited by 140
“Unfortunately, they have not paid enough attention to the effects of “aspects” (Wang et al. 2016) in the cross-domain sentiment classification task.”
BackgroundDetecting Cryptomining Malware: a Deep Learning Approach for Static and Dynamic Analysis
Darabian, H., Homayoun, S., Dehghantanha, A., Hashemi, S., Karimipour, H., Parizi, R. M., & Choo, K. R. (2020) · Journal of Grid Computing · doi:10.1007/s10723-020-09510-6 · Cited by 133
“As previously discussed, we utilized LSTM [20], ATT-LSTM [48], and CNN [35] to build our deep learning structure.”
MethodAspect-Category based Sentiment Analysis with Hierarchical Graph Convolutional Network
Cai, H., Tu, Y., Zhou, X., Yu, J., & Xia, R. (2020) · International Conference on Computational Linguistics · doi:10.18653/v1/2020.coling-main.72 · Cited by 159
“For the task of CSC, (Ruder et al., 2016; Wang et al., 2016; Xue and Li, 2018; Tay et al., 2018; Sun et al., 2019) proposed neural networks to make the most of context and aspect category information.”
MethodBai, X., Liu, P., & Zhang, Y. (2020) · IEEE/ACM Transactions on Audio Speech and Language Processing · doi:10.1109/taslp.2020.3042009 · Cited by 135
“Dominant methods for targeted sentiment employ neural network models to encode the input sentence and target mention [9], [10].”
MethodD’Aniello, G., Gaeta, M., & Rocca, I. L. (2022) · Artificial Intelligence Review · doi:10.1007/s10462-021-10134-9 · Cited by 134
“Convolutional Neural Network (CNN) for instance is used in Cahyadi and Khodra (2018); Maglogiannis et al. (2020); also approaches based on LSTM (Wang et al. 2016; Yu et al. 2019; Bao et al. 2019; Xing et al. 2019) and Recurrent Neural Networks (Al-Smadi et al. 2018; Nguyen and Shirai 2015; Colace…”
MethodDyadic Memory Networks for Aspect-based Sentiment Analysis
Tay, Y., Tuan, L. A., & Hui, S. C. (2017) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3132847.3132936 · Cited by 124
Meškelė, D., & Frăsincar, F. (2020) · Information Processing & Management · doi:10.1016/j.ipm.2020.102211 · Cited by 126
Deep learning approaches for Arabic sentiment analysis
Mohammed, A., & Kora, R. (2019) · Social Network Analysis and Mining · doi:10.1007/s13278-019-0596-4 · Cited by 125
Cheng, Y., Yao, L., Xiang, G., Zhang, G., Tang, T., & Zhong, L. (2020) · IEEE Access · doi:10.1109/access.2020.3005823 · Cited by 126
“Wang et al. [36] proposed an Attention-based Long Short-Term Memory Network for aspect-level sentiment classification, the model achieved state-of-the-art performance on aspect-level sentiment classification on SemEval 2014 dataset.”
MethodPhrase dependency relational graph attention network for Aspect-based Sentiment Analysis
Wu, H., Zhang, Z., Shi, S., Wu, Q., & Song, H. (2021) · Knowledge-Based Systems · doi:10.1016/j.knosys.2021.107736 · Cited by 125
Aspect Sentiment Classification with both Word-level and Clause-level Attention Networks
Wang, J., Li, J., Li, S., Kang, Y., Zhang, M., Si, L., & Zhou, G. (2018) · International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2018/617 · Cited by 133
Deep Learning in Sentiment Analysis: Recent Architectures
Abdullah, T., & Ahmet, A. (2022) · ACM Computing Surveys · doi:10.1145/3548772 · Cited by 134
“3 Recurrent Entity with Delayed Memory Update [154] ACC: 0.”
BackgroundEnhancing BERT Representation With Context-Aware Embedding for Aspect-Based Sentiment Analysis
Li, X., Fu, X., Xu, G., Yang, Y., Wang, J., Jin, L., Liu, Q., & Xiang, T. (2020) · IEEE Access · doi:10.1109/access.2020.2978511 · Cited by 131
“We use the results reported in XRCE [18], NRC-Canada [19], ATAE-LSTM [10] and BERT with auxiliary sentences [4].”
MethodHTML: Hierarchical Transformer-based Multi-task Learning for Volatility Prediction
Yang, L., Ng, T. L. J., Smyth, B., & Dong, R. (2020) · International World Wide Web Conference (WWW) · doi:10.1145/3366423.3380128 · Cited by 164
“These baselines can be grouped depending on whether they use historical pricing data [20, 29, 39, 57] (classical approaches), more recent uses of textual data [54, 64], or even more recent uses of multi-modal data [45, 46].”
BackgroundMethodEATN: An Efficient Adaptive Transfer Network for Aspect-level Sentiment Analysis
Zhang, K., Liu, Q., Qian, H., Xiang, B., Cui, Q., Zhou, J., & Chen, E. (2021) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2021.3075238 · Cited by 154
“As we demonstrated above, many DNN models [8], [9], [10] are proposed to automatically learn high-dimensional representations for aspects and their contexts [12].”
BackgroundMethodInfluentialXiao, L., Xue, Y., Wang, H., Hu, X., Gu, D., & Zhu, Y. (2021) · Neurocomputing · doi:10.1016/j.neucom.2021.10.091 · Cited by 122
Discrete Opinion Tree Induction for Aspect-based Sentiment Analysis
Chen, C., Teng, Z., Wang, Z., & Zhang, Y. (2022) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2022.acl-long.145 · Cited by 148
“…(ABSA) is the task of recognizing the sentiment polarities of specific aspect categories or aspect terms in a given sentence (Jiang et al., 2011; Dong et al., 2014; Wang et al., 2016; Tang et al., 2016; Li et al., 2018; Du et al., 2019; Sun et al., 2019a; Seoh et al., 2021; Xiao et al., 2021).”
BackgroundAspect based sentiment analysis by a linguistically regularized CNN with gated mechanism
Zeng, D., Dai, Y., Li, F., Wang, J., & Sangaiah, A. K. (2019) · Journal of Intelligent & Fuzzy Systems · doi:10.3233/jifs-169958 · Cited by 119
Aspect-based sentiment analysis with gated alternate neural network
Liu, N., & Shen, B. (2019) · Knowledge-Based Systems · doi:10.1016/j.knosys.2019.105010 · Cited by 125
BiSyn-GAT+: Bi-Syntax Aware Graph Attention Network for Aspect-based Sentiment Analysis
Liang, S., Wei, W., Mao, X.-L., Wang, F., & He, Z. (2022) · Findings of the Association for Computational Linguistics: ACL (Findings of ACL) · doi:10.18653/v1/2022.findings-acl.144 · Cited by 113
“Syntax-free methods: Neural networks with attention mechanisms (Wang et al., 2016; Chen et al., 2017; Song et al., 2019) have been widely used.”
MethodExploiting Coarse-to-Fine Task Transfer for Aspect-Level Sentiment Classification
Li, Z., Wei, Y., Zhang, Y., Zhang, X., & Li, X. (2019) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v33i01.33014253 · Cited by 131
Lee, G., Jeong, J., Seo, S., Kim, C., & Kang, P. (2018) · Knowledge-Based Systems · doi:10.1016/j.knosys.2018.04.006 · Cited by 110
Shankar, V., & Parsana, S. (2022) · Journal of the Academy of Marketing Science · doi:10.1007/s11747-022-00840-3 · Cited by 117
“In some cases, the labels are obtained from labeled datasets or surveys on Amazon Turk (e.g., Ghose et al., 2019; Wang et al., 2016).”
BackgroundLexicon-Enhanced LSTM With Attention for General Sentiment Analysis
Fu, X., Yang, J., Li, J., Fang, M., & Wang, H. H. (2018) · IEEE Access · doi:10.1109/access.2018.2878425 · Cited by 119
“propose the LSTM model with attention mechanism for the sentiment analysis of specific aspects [21].”
BackgroundMethodLan, M., Wang, J., Wu, Y., Niu, Z.-Y., & Wang, H. (2017) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/d17-1134 · Cited by 120
Enhancing Attention-Based LSTM With Position Context for Aspect-Level Sentiment Classification
Zeng, J., Ma, X., & Zhou, K. (2019) · IEEE Access · doi:10.1109/access.2019.2893806 · Cited by 114
“• AE-LSTM [25] is first to devise aspect embeddings which treat aspect representations as a part of training parameters.”
BackgroundMethodInfluentialEnsemble Multifeatured Deep Learning Models and Applications: A Survey
Abimannan, S., El-Alfy, E.-S. M., Chang, Y., Hussain, S., Shukla, S., & Satheesh, D. (2023) · IEEE Access · doi:10.1109/access.2023.3320042 · Cited by 119
“In a research study by Wang & Huang et al. [94], they demonstrated the effectiveness of ensemble models in sentiment analysis tasks, achieving state-of-the-art results on several benchmark datasets.”
BackgroundMethodInfluentialZheng, J., & Zheng, L. (2019) · IEEE Access · doi:10.1109/access.2019.2932619 · Cited by 112
“designed an attention mechanism that captured key parts of sentences to respond to text classification [27].”
BackgroundConstructing domain-dependent sentiment dictionary for sentiment analysis
Ahmed, M., Chen, Q., & Li, Z. (2020) · Neural Computing and Applications · doi:10.1007/s00521-020-04824-8 · Cited by 110
“ASE is a variant of ATAE-LSTM [44] that collaborates the aspect information and sentiment score to judge the aspect polarity.”
BackgroundMethodInfluentialA novel context-aware multimodal framework for persian sentiment analysis
Dashtipour, K., Gogate, M., Cambria, E., & Hussain, A. (2021) · Neurocomputing · doi:10.1016/j.neucom.2021.02.020 · Cited by 99
Dong, J., Chen, S., Miralinaghi, M., Chen, T., Li, P., & Labi, S. (2023) · Transportation Research Part C Emerging Technologies · doi:10.1016/j.trc.2023.104358 · Cited by 122
Deep Learning-Based Recommendation System: Systematic Review and Classification
Caiwen, L., Ishak, I., Ibrahim, H., Zolkepli, M., Sidi, F., & Li, C. (2023) · IEEE Access · doi:10.1109/access.2023.3323353 · Cited by 129
MASAD: A large-scale dataset for multimodal aspect-based sentiment analysis
Zhou, J., Zhao, J., Huang, J. X., Hu, Q., & He, L. (2021) · Neurocomputing · doi:10.1016/j.neucom.2021.05.040 · Cited by 117
Zhang, G., & Etemad, A. (2021) · IEEE Transactions on Neural Systems and Rehabilitation Engineering · doi:10.1109/tnsre.2021.3089594 · Cited by 111
“The LSTM-CNN architecture employs CNN-based attention with the same parameters as the baseline CNN model and the LSTM-SoftAtt model employs the same soft attention mechanism as described in [31].”
BackgroundMethodDIRT: Deep Learning Enhanced Item Response Theory for Cognitive Diagnosis
Cheng, S., Liu, Q., Chen, E., Huang, Z., Huang, Z., Chen, Y., Ma, H., & Hu, G. (2019) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3357384.3358070 · Cited by 157
“Deep learning is a state-of-the-art method for many applications, e.g., image recognition [ Krizhevsky et al. , 2012 ] and natural language processing [ Wang et al. , 2016 ] .”
MethodProgressive Self-Supervised Attention Learning for Aspect-Level Sentiment Analysis
Tang, J., Lu, Z., Su, J., Ge, Y., Song, L., Sun, L., & Luo, J. (2019) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/p19-1053 · Cited by 114
“Recently, with the rapid development of deep learning, dominant ASC models have evolved into neural network (NN) based models (Tang et al., 2016b; Wang et al., 2016; Tang et al., 2016a; Ma et al., 2017; Chen et al., 2017; Li et al., 2018; Wang et al., 2018), which are able to automatically learn…”
BackgroundA Survey of Cutting-edge Multimodal Sentiment Analysis
Singh, U., Abhishek, K., & Azad, H. K. (2024) · ACM Computing Surveys · doi:10.1145/3652149 · Cited by 134
“CNN model [150], rule-based model [168, 249], memory network [310], attention mechanism [333], CRFs sequential model [288], topic model [195] are some aspect-level SAs which try to build a relationship between opinion holder and their aspect.”
MethodLearning Latent Opinions for Aspect-level Sentiment Classification
Wang, B., & Lu, W. (2018) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v32i1.12020 · Cited by 106
“Also, target extraction task (Zhao et al. 2010; Wang et al. 2016a) can be added to this joint learning framework.”
BackgroundMethodInfluentialFCCA: Hybrid Code Representation for Functional Clone Detection Using Attention Networks
Hua, W., Sui, Y., Wan, Y., Liu, G., & Xu, G. (2020) · IEEE Transactions on Reliability · doi:10.1109/tr.2020.3001918 · Cited by 124
“1, the method statements “ ret = ret * power; ” at line 7 in “ Func() ” and “ z = p * i; ” at line 5 in “ CloneT4() ” can be represented us-ing the same operation, i.e., “ Binary Expr ” (multiplication) when using an AST with two child nodes (* denotes multiplication in the two statements).”
BackgroundMethodGündüz, H. (2021) · Financial Innovation · doi:10.1186/s40854-021-00243-3 · Cited by 103
Paradigm Shift in Natural Language Processing
Sun, T.-X., Liu, X.-Y., Qiu, X.-P., & Huang, X.-J. (2022) · Machine Intelligence Research · doi:10.1007/s11633-022-1331-6 · Cited by 86
Understanding More About Human and Machine Attention in Deep Neural Networks
Lai, Q., Khan, S. H., Nie, Y., Sun, H., Shen, J., & Shao, L. (2020) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2020.3007321 · Cited by 113
Integrating external knowledge into aspect-based sentiment analysis using graph neural network
Gu, T., Zhao, H., He, Z., Li, M., & Ying, D. (2022) · Knowledge-Based Systems · doi:10.1016/j.knosys.2022.110025 · Cited by 112
Cross-modal fine-grained alignment and fusion network for multimodal aspect-based sentiment analysis
Xiao, L., Wu, X., Yang, S., Xu, J., Zhou, J., & He, L. (2023) · Information Processing & Management · doi:10.1016/j.ipm.2023.103508 · Cited by 131
Hierarchical Attention Based Position-Aware Network for Aspect-Level Sentiment Analysis
Li, L., Liu, Y., & Zhou, A. (2018) · Conference on Computational Natural Language Learning · doi:10.18653/v1/k18-1018 · Cited by 119
“Wang et al., (2016) proposed an attention based LSTM which introduced the aspect clues by concatenating the aspect embeddings and the word representations.”
Background
Metadata
- Authors
- Wang, Y., Huang, M., zhu, X., & Zhao, L.
- Affiliations
- State Key Laboratory of Intelligent Technology and Systems (CN)
- Venue
- Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing
- Published
- 2016
- Pages
- 606-615
- OpenAlex
- W2562607067
- Cited by
- 2,450
- References
- 33
- Citations by year
- 2026: 108 · 2025: 179 · 2024: 272 · 2023: 332 · 2022: 356 · 2021: 401 · 2020: 343 · 2019: 285 · 2018: 134 · 2017: 28
- FWCI
- 80.28
- Type
- conference paper
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- cc-by
- Locations
- Conference on Empirical Methods in Natural Language Processing (EMNLP) (publishedVersion, cc-by)
- Funders
- National Natural Science Foundation of China (2012CB316301, 973 Program, 2013CB329403, 61272227, 61332007)
- Tsinghua University
- Samsung
- Beijing Higher Education Young Elite Teacher Project
- National Key Research and Development Program of China (2012CB316301, 61332007, 2013CB329403)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Sentiment Analysis and Opinion Mining
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Social Sciences › Decision Sciences › Management Science and Operations Research › Stock Market Forecasting Methods
- Keywords
- aspect-based sentiment analysis, attention mechanism, long short-term memory, sentiment polarity, SemEval-2014, fine-grained sentiment analysis
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.