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 501–600 of 1,003
Building a Twitter Sentiment Analysis System with Recurrent Neural Networks
Nistor, S. C., Moca, M., Moldovan, D., Oprean, D. B., & NISTOR, R. L. (2021) · Sensors · doi:10.3390/s21072266 · Cited by 44
“[25] introduced an attentionbased long short-term memory network in order to focus on the aspect-level sentiment classification, managing to only slightly improve the benchmark models.”
BackgroundBody, T., Tao, X., Li, Y., Li, L., & Zhong, N. (2021) · Expert Systems with Applications · doi:10.1016/j.eswa.2021.115033 · Cited by 44
Feng, A., Zhang, X., & Song, X. (2022) · IEEE Access · doi:10.1109/access.2022.3142178 · Cited by 42
“ATAE-LSTM [13] attaches aspect terms to the representation of each word in the sentence.”
BackgroundMethodInfluentialInvestigating the role of swear words in abusive language detection tasks
Pamungkas, E. W., Basile, V., & Patti, V. (2022) · Language Resources and Evaluation · doi:10.1007/s10579-022-09582-8 · Cited by 41
“This particular model (AT-LSTM) (Wang et al. 2016) has an attention mechanism which captures the important part of a sentence by focusing on the given aspect.”
BackgroundMethodInfluentialMinority shareholder activism and corporate social responsibility
Xu, S., Yin, B., & Lou, C. (2022) · Economic Modelling · doi:10.1016/j.econmod.2022.106045 · Cited by 41
Zhai, Z., Chen, H., Feng, F., Li, R., & Wang, X. (2022) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2022.emnlp-main.212 · Cited by 55
“…Yin et al., 2016; Li et al., 2018b; Xu et al., 2018; Ma et al., 2019; Chen and Qian, 2020; Wei et al., 2020), Aspect Sentiment Classification (ASC) (Wang et al., 2016b; Tang et al., 2016; Ma et al., 2017; Fan et al., 2018; Li et al., 2018a; Zhang et al., 2019; Sun et al., 2019; Wang et al., 2020;…”
BackgroundMethodInfluentialZheng, Y., Li, X., & Nie, J. (2023) · Information Sciences · doi:10.1016/j.ins.2023.03.102 · Cited by 40
An integrated approach for prediction of magnitude using deep learning techniques
Joshi, A., Raman, B., & Mohan, C. K. (2024) · Neural Computing and Applications · doi:10.1007/s00521-024-09891-9 · Cited by 40
“It was studied that the performance of LSTM in various areas, such as classification of captured sentiments, machine translation and speech recognition, could be enhanced using attention mechanism [21–23].”
A hybrid approach for generating reputation based on opinions fusion and sentiment analysis
Benlahbib, A., & Nfaoui, E. H. (2019) · Journal of Organizational Computing and Electronic Commerce · doi:10.1080/10919392.2019.1654350 · Cited by 42
“Wang et al. (2016) proposed an Attention-based Long Short-Term Memory Network for aspect-level sentiment classification.”
MethodMulti-Attention Multimodal Sentiment Analysis
Kim, T., & Lee, B. (2020) · International Conference on Multimedia Retrieval · doi:10.1145/3372278.3390698 · Cited by 40
“To capture the key parts of the sequential data, recent works [17, 31, 34] have been augmenting LSTM/GRU models with the attention mechanism.”
MethodZhu, X., Zhu, Y., Zhang, L., & Chen, Y. (2022) · Applied Intelligence · doi:10.1007/s10489-022-03702-1 · Cited by 42
“This method connects the aspect target [5] or aspect category [8, 12] embedding to each context embedding to achieve the interactions be-tween aspect semantics and its contexts.”
BackgroundMethodInfluentialSelf-citationLin, T., & Joe, I. (2023) · IEEE Access · doi:10.1109/access.2023.3270927 · Cited by 41
“The ATAE-LSTM [24] combines attention and LSTM and uses attention to obtain more important contextual information for different aspects to solve the aspect-level sentiment analysis problem.”
MethodRecognizing Conflict Opinions in Aspect-level Sentiment Classification with Dual Attention Networks
Tan, X., Cai, Y., & Zhu, C. (2019) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/d19-1342 · Cited by 44
“Faced with conflict opinions, existing attention-based models (Wang et al., 2016) (with single attention) usually attend on a portion of a conflict expression and ignore the other portion, which make its predicted result prone to be positive or negative .”
BackgroundInfluentialACR-SA: attention-based deep model through two-channel CNN and Bi-RNN for sentiment analysis
Kamyab, M., Liu, G., Rasool, A., & Adjeisah, M. (2022) · PeerJ Computer Science · doi:10.7717/peerj-cs.877 · Cited by 43
“, 2010), document level (Yessenalina, Yue & Cardie, 2010), aspect-based level (Hu & Liu, 2004; Wang et al., 2016b).”
Dai, A., Hu, X., Nie, J., & Chen, J. (2022) · International Journal of Data Science and Analytics · doi:10.1007/s41060-022-00315-2 · Cited by 39
Influenza surveillance with Baidu index and attention-based long short-term memory model
Dai, S., & Han, L. (2023) · PLoS ONE · doi:10.1371/journal.pone.0280834 · Cited by 40
“Although the attention-based LSTM model has been used in the field of financial marketing [29], machine translation [30], sentiment classification [31] and even in the application of fitting illness cases [32], our contribution is first introducing this method to engage with the Baidu Index in the…”
MethodImproving aspect-based sentiment analysis with contrastive learning
Xu, L., & Wang, W. (2023) · Natural Language Processing Journal · doi:10.1016/j.nlp.2023.100009 · Cited by 53
A survey on aspect base sentiment analysis methods and challenges
Wankhade, M., Kulkarni, C., & Rao, A. C. S. (2024) · Applied Soft Computing · doi:10.1016/j.asoc.2024.112249 · Cited by 44
Microblog sentiment analysis with weak dependency connections
Xiaomei, Z., Yang, J., Jianpei, Z., & Hongyu, H. (2017) · Knowledge-Based Systems · doi:10.1016/j.knosys.2017.11.035 · Cited by 40
Hidden topic–emotion transition model for multi-level social emotion detection
Tang, D., Zhang, Z., He, Y., Lin, C., & Zhou, D. (2018) · Knowledge-Based Systems · doi:10.1016/j.knosys.2018.11.014 · Cited by 38
Variational Semi-Supervised Aspect-Term Sentiment Analysis via Transformer
Cheng, X., Xu, W., Wang, T., Chu, W., Huang, W., Chen, K., & Hu, J. (2019) · Conference on Computational Natural Language Learning · doi:10.18653/v1/k19-1090 · Cited by 39
“, 2018), AE-LSTM, ATAELSTM (Wang et al., 2016), GCAE (Li and Xue, 2018), from the original paper.”
BackgroundDNet: A lightweight and efficient model for aspect based sentiment analysis
Ren, F., Feng, L., Xiao, D., Cai, M., & Cheng, S. (2020) · Expert Systems with Applications · doi:10.1016/j.eswa.2020.113393 · Cited by 41
ScenarioSA: A Dyadic Conversational Database for Interactive Sentiment Analysis
Zhang, Y., Zhao, Z., Wang, P., Li, X., Rong, L., & Song, D. (2020) · IEEE Access · doi:10.1109/access.2020.2994147 · Cited by 38
“Finally, we design a comparative experiment on Scenar-ioSA over a number of typical sentiment analysis models, including a lexicon-based approach (which is SentiStrength), two machine learning based algorithms (which are support vector machine and joint sentiment/topic model), four popular neural network approaches: a…”
MethodInfluentialPartial discharge detection of insulated conductors based on CNN-LSTM of attention mechanisms
Li, Z., Qu, N., Li, X., Zuo, J., & Yin, Y. (2021) · Journal of Power Electronics · doi:10.1007/s43236-021-00239-3 · Cited by 38
“However, these networks are prone to losing sequence information when the input time series is lengthy [29, 30].”
BackgroundWhat’s in a name? – gender classification of names with character based machine learning models
Hu, Y., Hu, C., Tran, T., Kasturi, T., Joseph, E. L., & Gillingham, M. (2021) · Data Mining and Knowledge Discovery · doi:10.1007/s10618-021-00748-6 · Cited by 38
“Note that we do not further compare with other attention-based models such as Attention-based RNN [9, 34, 42] because char-BERT, which originated from BERT [14], is a purely attentive transformer network, and has outperformed all previous models.”
ResultAn Iterative Multi-Knowledge Transfer Network for Aspect-Based Sentiment Analysis
Liang, Y., Meng, F., Zhang, J., Chen, Y., Xu, J., & Zhou, J. (2021) · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · doi:10.18653/v1/2021.findings-emnlp.152 · Cited by 52
“The opinion terms of these three datasets are annotated by Wang et al. (2016a).”
Aspect-Based Sentiment Analysis in Hindi Language by Ensembling Pre-Trained mBERT Models
Pathak, A., Kumar, S., Roy, P. P., & Kim, B. (2021) · Electronics · doi:10.3390/electronics10212641 · Cited by 43
“In [21], Attention‑Based LSTM with Aspect Embedding (ATAE‑LSTM) was proposed, which focused on identifying the sentiment‑carrying words that were relatively correlated with the entity or target.”
MethodChandra, R., & Ranjan, M. (2022) · PLoS ONE · doi:10.1371/journal.pone.0273476 · Cited by 50
“LSTM models have been improved for language modelling using attention based mechanisms [43], and encoder-decoder LSTM framework with attention (Transformer) [44,45].”
MethodLu, Q., Sun, X., Sutcliffe, R. F. E., Xing, Y., & Zhang, H. (2022) · Knowledge-Based Systems · doi:10.1016/j.knosys.2022.109840 · Cited by 43
Unified Instance and Knowledge Alignment Pretraining for Aspect-Based Sentiment Analysis
Liu, J., Zhong, Q., Ding, L., Jin, H., Du, B., & Tao, D. (2023) · IEEE/ACM Transactions on Audio Speech and Language Processing · doi:10.1109/taslp.2023.3290431 · Cited by 48
“Specifically, the original ATAE-LSTM pays considerable attention to the unrelated opinion word “Great”, resulting in a false prediction.”
BackgroundMethodInfluentialHow developments in natural language processing help us in understanding human behaviour
Mihalcea, R., Biester, L., Boyd, R., Jin, Z., Pérez-Rosas, V., Wilson, S., & Pennebaker, J. (2024) · Nature Human Behaviour · doi:10.1038/s41562-024-01938-0 · Cited by 42
“…learning, which involve methods for transforming words or entities into high-dimensional vectors in a way that captures their contextual and semantic relationships, including, among others, algorithms such as recurrent neural networks 73 , attention 74,75 and adversarial learning 76 .”
Target-aware convolutional neural network for target-level sentiment analysis
Hyun, D., Park, C., Yang, M.-C., Song, I., Lee, J., & Yu, H. (2019) · Information Sciences · doi:10.1016/j.ins.2019.03.076 · Cited by 40
Aspect-Based Sentiment Classification Using Interactive Gated Convolutional Network
Kumar, A., Narapareddy, V. T., Veerubhotla, A. S., Neti, L. B. M., & Malapati, A. (2020) · IEEE Access · doi:10.1109/access.2020.2970030 · Cited by 39
“In the recent past, some researchers have designed deep neural networks using targets and their review contexts and achieved a promising result on the aspect-level sentiment classification task [5], [7], [29], [30].”
BackgroundFu, D., Weber, C., Yang, G., Kerzel, M., Nan, W., Barros, P. V. A., Wu, H., Liu, X., & Wermter, S. (2020) · Frontiers in Integrative Neuroscience · doi:10.3389/fnint.2020.00010 · Cited by 42
“, 2017), sentiment classification (Wang et al., 2016), visual question answering (Li et al.”
BackgroundA Lexicon-Enhanced Attention Network for Aspect-Level Sentiment Analysis
Ren, Z., Zeng, G., Chen, L., Zhang, Q., Zhang, C., & Pan, D. (2020) · IEEE Access · doi:10.1109/access.2020.2995211 · Cited by 39
“But this method does not capture the features in some aspect term of the sentence [13].”
MethodInfluentialMemory network with hierarchical multi-head attention for aspect-based sentiment analysis
Chen, Y., Zhuang, T., & Guo, K. (2021) · Applied Intelligence · doi:10.1007/s10489-020-02069-5 · Cited by 39
“ATAE-LSTM used the concatenation of aspect embeddings and context word embedding as the input for LSTM, thereby enabling aspect embeddings to take part in the computation of attention weights for each context word in an attention layer.”
BackgroundMethodInfluentialStock Price Prediction using Machine Learning and Sentiment Analysis
Mehta, Y., Malhar, A., & Shankarmani, R. (2021) · International Conference for Emerging Technology (INCET) · doi:10.1109/incet51464.2021.9456376 · Cited by 40
“This method of characteristic sorting with the help of the Genetic algorithm[14] can be used as a preprocessing step which can then be considered to point out chief technical measures which in turn is more helpful to the traders and can be simply calculated using the closing price.”
MethodA multi-task learning framework for end-to-end aspect sentiment triplet extraction
Chen, F., Yang, Z., & Huang, Y. (2022) · Neurocomputing · doi:10.1016/j.neucom.2022.01.021 · Cited by 39
A context-sensitive multi-tier deep learning framework for multimodal sentiment analysis
Ganeshkumar, P., Vijay, S. A. A., Prakash, J., V, Paul, A., & Nayyar, A. (2023) · Multimedia Tools and Applications · doi:10.1007/s11042-023-17601-1 · Cited by 47
Microblog sentiment analysis via embedding social contexts into an attentive LSTM
Yang, J., Zou, X., Zhang, W., & Han, H. (2020) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2020.104048 · Cited by 37
A prompt model with combined semantic refinement for aspect sentiment analysis
Zhu, X., Kuang, Z., & Zhang, L. (2023) · Information Processing & Management · doi:10.1016/j.ipm.2023.103462 · Cited by 40
Self-citationA Human-Like Semantic Cognition Network for Aspect-Level Sentiment Classification
Lei, Z., Yang, Y., Yang, M., Zhao, W. D., Guo, J. F., & Liu, Y. (2019) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v33i01.33016650 · Cited by 40
“Wang et al. (2016) proposed to learn an embedding vector for each aspect, and these aspect embeddings were used to calculate the attention weights to capture important information with regard to a given aspect.”
MethodSemantic and syntactic analysis in learning representation based on a sentiment analysis model
Vo, A.-D., Nguyen, Q.-P., & Ock, C.-Y. (2019) · Applied Intelligence · doi:10.1007/s10489-019-01540-2 · Cited by 38
“Meanwhile, Wang et al. [72] and Chen et al. [73] proposed LSTM-based methods for aspect-level sentiment identification and classification.”
MethodAspect-Specific Heterogeneous Graph Convolutional Network for Aspect-Based Sentiment Classification
Xu, K., Zhao, H., & Liu, T. (2020) · IEEE Access · doi:10.1109/access.2020.3012637 · Cited by 39
Adversarial Attack and Defense of Structured Prediction Models
Han, W., Zhang, L., Jiang, Y., & Tu, K. (2020) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2020.emnlp-main.182 · Cited by 49
Machine Learning for Sleep Apnea Detection with Unattended Sleep Monitoring at Home
Kristiansen, S., Nikolaidis, K., Plagemann, T., Goebel, V., Traaen, G. M., Øverland, B., Aakerøy, L., Hunt, T.-E., Loennechen, J. P., Steinshamn, S., et al. (2021) · ACM Transactions on Computing for Healthcare · doi:10.1145/3433987 · Cited by 36
“The attention-vectors learned by classifiers such as BIWALSTM have previously been helpful to interpret the decisions of recurrent NN [48].”
BackgroundCross-domain sentiment classification via parameter transferring and attention sharing mechanism
Zhao, C., Wang, S., Li, D., Liu, X., Yang, X., & Liu, J. (2021) · Information Sciences · doi:10.1016/j.ins.2021.07.001 · Cited by 36
Semantic Relatedness Enhanced Graph Network for aspect category sentiment analysis
Zhou, T., & Law, K. M. Y. (2022) · Expert Systems with Applications · doi:10.1016/j.eswa.2022.116560 · Cited by 42
Hierarchical dual graph convolutional network for aspect-based sentiment analysis
Zhou, T., Shen, Y., Chen, K., & Cao, Q. (2023) · Knowledge-Based Systems · doi:10.1016/j.knosys.2023.110740 · Cited by 38
Kandhro, I. A., Ali, F., Uddin, M., Kehar, A., & Manickam, S. (2024) · Knowledge and Information Systems · doi:10.1007/s10115-024-02104-8 · Cited by 35
Using neural attention networks to detect adverse medical events from electronic health records
Chu, J., Dong, W., He, K., Duan, H., & Huang, Z. (2018) · Journal of Biomedical Informatics · doi:10.1016/j.jbi.2018.10.002 · Cited by 37
Adversarial Attention Modeling for Multi-dimensional Emotion Regression
Zhu, S., Li, S., & Zhou, G. (2019) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/p19-1045 · Cited by 40
“Typically, studies in emotion analysis can be divided into either emotion classification (Yang et al., 2007; Tripathi et al., 2017) or emotion regression (Yu et al., 2015; Wang et al., 2016a).”
BackgroundMethodInfluentialLi, J., Yu, J., Ye, Z., Wong, K. H., Mak, M., Mak, B. K.-W., Liu, X., & Meng, H. M. L. (2021) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp39728.2021.9414147 · Cited by 35
AMR-based Network for Aspect-based Sentiment Analysis
Ma, F., Hu, X., Liu, A., Yang, Y., Li, S., Yu, P. S., & Wen, L. (2023) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2023.acl-long.19 · Cited by 59
“To this end, some previous studies (Wang et al., 2016; Chen et al., 2017; Gu et al., 2018; Du et al., 2019; Liang et al., 2019; Xing et al., 2019) have devoted the main efforts to attention mechanisms.”
BackgroundSpan-level Aspect-based Sentiment Analysis via Table Filling
Mao, Z., Zhu, Y., Liu, Z., Bao, Z., Wu, Y., Sun, X. W., & Xu, L. (2023) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/2023.acl-long.515 · Cited by 35
“In this subsection, we briefly summarize the baseline models we compare to in the experiments: (1) ATAE-LSTM (Wang et al., 2016) combines the attention mechanism with the LSTM network and uses extra aspect embeddings to obtain the aspect-specific representations (2) IAN (Ma et al.”
BackgroundMethodInfluentialLSOIT: Lexicon and Syntax Enhanced Opinion Induction Tree for Aspect-based Sentiment Analysis
Wu, H., Zhou, D., Sun, C., Zhang, Z., Ding, Y. S., & Chen, Y. (2023) · Expert Systems with Applications · doi:10.1016/j.eswa.2023.121137 · Cited by 35
Zhao, Q., Yang, F., An, D., & Lian, J. (2024) · Sensors · doi:10.3390/s24020418 · Cited by 37
“• ATAE-LSTM [5]: The ATAE-LSTM model utilizes an attention-based LSTM model to compute attention scores for specific aspects, thus enabling the model to focus on pivotal contextual information around different aspects in the sentence.”
MethodA Low-Power LSTM Processor for Multi-Channel Brain EEG Artifact Detection
Hasib-Al-Rashid, Manjunath, N. K., Paneliya, H., Hosseini, M., Hairston, W. D., & Mohsenin, T. (2020) · International Symposium on Quality Electronic Design (ISQED) · doi:10.1109/isqed48828.2020.9137056 · Cited by 35
“Recurrent Neural Network (RNN) and its variance Long Short Time Memory are favored now-a-days in the literature for learning time sequence data such as sentiment analysis, and so on [12].”
BackgroundSyntax-Aware Aspect Level Sentiment Classification with Graph Attention NetworksPreprint
Huang, B., & Carley, K. M. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1909.02606 · Cited by 37
“Wang et al. (2016) introduce the attention mechanism into this task (Bahdanau et al., 2014).”
BackgroundMethodInfluentialAziz, M. M., Bakar, A. A., & Yaakub, M. R. (2024) · Journal of King Saud University - Computer and Information Sciences · doi:10.1016/j.jksuci.2024.102035 · Cited by 34
“• ATAE-LSTM (Wang et al., 2016): Combines aspect embedding with word embedding at the input layer of an ATAE-LSTM network to deepen the weighting scheme.”
Yang, J., Yang, R., Lu, H., Wang, C., & Xie, J. (2019) · ACM Transactions on Asian and Low-Resource Language Information Processing · doi:10.1145/3321125 · Cited by 35
“Our CEA and DT-CEA methods perform better than ATAE-LSTM++ and DMN++ on all the length intervals, showing their effectiveness.”
BackgroundMethodInfluentialRGCN: Recurrent Graph Convolutional Networks for Target-Dependent Sentiment Analysis
Chen, J., Hou, H., Gao, J., Ji, Y., & Bai, T. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-29551-6_59 · Cited by 44
Application of Deep Learning Approaches for Sentiment Analysis
Pathak, A. R., Agarwal, B., Pandey, M., & Rautaray, S. S. (2020) · Algorithms for intelligent systems · doi:10.1007/978-981-15-1216-2_1 · Cited by 44
Interactive POS-aware network for aspect-level sentiment classification
Shuang, K., Gu, M., Li, R., Loo, J., & Su, S. (2020) · Neurocomputing · doi:10.1016/j.neucom.2020.08.013 · Cited by 38
Zhang, M., Palade, V., Wang, Y., & Ji, Z. (2020) · Information Sciences · doi:10.1016/j.ins.2020.09.038 · Cited by 36
“For example, in (Wang et al., 2016), an attention weight vector was proposed to determine the importance of words in a sentence given an aspect, the weights of which can be further used to scale the hidden states of a LSTM model and thus obtain the weighted representation for a sentence.”
BackgroundMethodSelf-citationTransformer Based Multi-Grained Attention Network for Aspect-Based Sentiment Analysis
Sun, J., Han, P., Cheng, Z., Wu, E., & Wang, W. (2020) · IEEE Access · doi:10.1109/access.2020.3039470 · Cited by 35
“Wang et al. [36] proposed an LSTM model combined with attention mechanism, which inputs the specific aspects of vectorization into the LSTM network, so that the model can focus on the feature information of specific aspects in the training process, so as to improve the result of sentiment…”
BackgroundMethodInfluentialCross-modal image sentiment analysis via deep correlation of textual semantic
Zhang, K., Zhu, Y., Zhang, W., & Zhu, Y. (2021) · Knowledge-Based Systems · doi:10.1016/j.knosys.2021.106803 · Cited by 39
Wu, H., & Liu, H. (2021) · Sustainable Energy Grids and Networks · doi:10.1016/j.segan.2021.100490 · Cited by 34
Zhao, L. L., Liu, Y., Zhang, M., Guo, T., & Chen, L. (2021) · Information Processing & Management · doi:10.1016/j.ipm.2021.102641 · Cited by 36
Self-citationTwo-stage prediction of machinery fault trend based on deep learning for time series analysis
Xu, H., Ma, R., Li, Y., & Ma, Z. (2021) · Digital Signal Processing · doi:10.1016/j.dsp.2021.103150 · Cited by 36
Aspect-based sentiment analysis with graph convolution over syntactic dependencies
Žunić, A., Corcoran, P., & Spasić, . (2021) · Artificial Intelligence in Medicine · doi:10.1016/j.artmed.2021.102138 · Cited by 36
“9% on classifying customer reviews into positive and negative sentiment, respectively [7].”
BackgroundMethodAspect‐Level Sentiment Analysis Approach via BERT and Aspect Feature Location Model
Pang, G., Lu, K., Zhu, X., He, J., Mo, Z., Peng, Z., & Pu, B. (2021) · Wireless Communications and Mobile Computing · doi:10.1155/2021/5534615 · Cited by 36
“In order to verify the effectiveness of our model, we compare the ALM-BERT approach with many popular aspect-based sentiment analysis models, as listed in the following: (i) TD-LSTM [26] is a classic model, which improves the accuracy of classification by integrating the correlation information between aspect words an…”
BackgroundMethodSelf-citationJoint Learning With BERT-GCN and Multi-Attention for Event Text Classification and Event Assignment
She, X., Chen, J., & Chen, G. (2022) · IEEE Access · doi:10.1109/access.2022.3156918 · Cited by 37
“Meanwhile, to further increase the representation accuracy of such models, attention mechanisms have been introduced as an integral part of text classification models [28, 29].”
BackgroundText sentiment analysis based on BERT-CBLBGA
Jia, K., Meng, F., Liang, J., & Gong, P. (2023) · Computers & Electrical Engineering · doi:10.1016/j.compeleceng.2023.109019 · Cited by 34
Unified ABSA via Annotation-Decoupled Multi-Task Instruction Tuning
Wang, Z., Xia, R., & Yu, J. (2024) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2024.3392836 · Cited by 45
“Early studies mainly focus on Aspect-Based Sentiment Classifica-tion (ABSC) [11], [12], [13], [14].”
BackgroundUniSA: Unified Generative Framework for Sentiment Analysis
Li, Z., Lin, T.-E., Wu, Y., Liu, M., Tang, F., Zhao, M., & Li, Y. (2023) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3581783.3612336 · Cited by 55
“have employed the attention mechanism integrated with LSTMbased neural network models to model the relationship between aspects and their contextual words [33, 37, 66].”
MethodAspect-based sentiment analysis: approaches, applications, challenges and trends
Nath, D., & Dwivedi, S. K. (2024) · Knowledge and Information Systems · doi:10.1007/s10115-024-02200-9 · Cited by 42
Learning Domain-Sensitive and Sentiment-Aware Word Embeddings
Shi, B., Fu, Z., Bing, L., & Lam, W. P. (2018) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/p18-1232 · Cited by 38
“Some researchers focus on designing RNN or CNN based models for predicting sentence level (Kim, 2014) or aspect level sentiment (Li et al., 2018; Chen et al., 2017; Wang et al., 2016).”
BackgroundAspect-Based Sentiment Analysis with New Target Representation and Dependency Attention
Yang, T., Yin, Q., Yang, L., & Wu, O. (2019) · IEEE Transactions on Affective Computing · doi:10.1109/taffc.2019.2945028 · Cited by 34
SOBA: Semi-automated Ontology Builder for Aspect-based sentiment analysis
Zhuang, L., Schouten, K., & Frăsincar, F. (2019) · Journal of Web Semantics · doi:10.1016/j.websem.2019.100544 · Cited by 33
Interactive Rule Attention Network for Aspect-Level Sentiment Analysis
Lu, Q., Zhu, Z., Zhang, D., Wu, W., & Guo, Q. (2020) · IEEE Access · doi:10.1109/access.2020.2981139 · Cited by 33
“AE-LSTM [41]: AE-LSTM first proposes aspect embedding, and generates attention vector by combining aspect embedding with hidden state.”
BackgroundMethodInfluentialXiao, L., Hu, X., Chen, Y., Xue, Y., Chen, B., Gu, D., & Tang, B. (2020) · Multimedia Tools and Applications · doi:10.1007/s11042-020-10107-0 · Cited by 38
“Attention becomes an indispensable module in nearly every NLP model and showing promising results in ABSC [20, 22, 37].”
BackgroundMethodResultFei, H., Ren, Y., Wu, S., Li, B., & Ji, D. (2021) · International World Wide Web Conference (WWW) · doi:10.1145/3442381.3449789 · Cited by 40
“, sentences, twitters) [12, 24, 35, 50, 53, 54], while another line of efforts are devoted to the document-level sentiment analysis [38, 52, 62, 63] for long document texts.”
BackgroundA Dual-Channel Framework for Sarcasm Recognition by Detecting Sentiment Conflict
Liu, Y., Wang, Y., Sun, A., Meng, X., Li, J., & Guo, J. (2022) · Findings of the Association for Computational Linguistics: NAACL · doi:10.18653/v1/2022.findings-naacl.126 · Cited by 33
Self-citationComplete quadruple extraction using a two-stage neural model for aspect-based sentiment analysis
Zhang, H., Chen, Z., Chen, B. Y., Hu, B., Li, M., Yang, C., & Jiang, B. (2022) · Neurocomputing · doi:10.1016/j.neucom.2022.04.027 · Cited by 35
Fan, S., Yu, H., Cai, X., Geng, Y., Li, G., Xu, W., Wang, X., & Yang, Y. (2022) · Information Sciences · doi:10.1016/j.ins.2022.06.089 · Cited by 33
Letting Emotions Flow: Success Prediction by Modeling the Flow of Emotions in Books
Maharjan, S., Kar, S., Montes-y-Gómez, M., Gonzalez, F. A., & Solorio, T. (2018) · Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT) · doi:10.18653/v1/n18-2042 · Cited by 41
Recent Advances in Stock Market Prediction Using Text Mining: A Survey
Alzazah, F., & Cheng, X. (2020) · IntechOpen eBooks · doi:10.5772/intechopen.92253 · Cited by 32
Jiang, H., Chen, X., Miao, D., Zhang, H., Qin, X., Gu, X., Lu, P., & Li, X. (2025) · Applied Intelligence · doi:10.1007/s10489-025-06313-8 · Cited by 34
Aghajanian, S., Mohammadifard, F., Mohammadi, I., Firouzabadi, S. R., Bagheri, A. B., Ghaffary, E. M., & Mirmosayyeb, O. (2025) · Alzheimer s Research & Therapy · doi:10.1186/s13195-025-01827-2 · Cited by 41
“Rather than relying solely on the last hidden state, we introduced an attention mechanism [32, 33] to allow the model to weight each time point’s representation, primarily to understand the influence and importance of information contribution per MRI visit.”
ReEL: Review Aware Explanation of Location Recommendation
Baral, R., Zhu, X., Iyengar, S. S., & Li, T. (2018) · ACM Conference on User Modeling, Adaptation and Personalization (UMAP) · doi:10.1145/3209219.3209237 · Cited by 44
Self-citationIs position important? deep multi-task learning for aspect-based sentiment analysis
Zhou, J., Huang, J. X., Hu, Q., & He, L. (2020) · Applied Intelligence · doi:10.1007/s10489-020-01760-x · Cited by 33
“– ATAE-LSTM integrates target embedding into each word embedding and hidden vector to enhance the effect of target embedding with attention mechanism [43].”
Attention Meets Perturbations: Robust and Interpretable Attention With Adversarial Training
Kitada, S., & Iyatomi, H. (2021) · IEEE Access · doi:10.1109/access.2021.3093456 · Cited by 36
“Today, these mechanisms contribute to improving the prediction performance of various tasks in the NLP field, such as sentence-level classification [2], sentiment analysis [3], question answering [4], and natural language inference [5].”
BackgroundA Multi-Layer Network for Aspect-Based Cross-Lingual Sentiment Classification
Sattar, K., Umer, Q., Vasbieva, D. G., Chung, S., Latif, Z., & Lee, C. (2021) · IEEE Access · doi:10.1109/access.2021.3116053 · Cited by 34
“other researchers [10], [11], [17], [18] also adopted neural network-based models for targeted sentiment classification.”
BackgroundExploring rich structure information for aspect-based sentiment classification
Zhu, L., Zhu, X., Guo, J., & Dietze, S. (2022) · Journal of Intelligent Information Systems · doi:10.1007/s10844-022-00729-1 · Cited by 32
“Wang et al. (2016) develop an aspect-to sentence attention mechanism to enforce the model to attend to the important context words.”
BackgroundMethodSelf-citationGascó, L., Clavel, C., Asensio, C., & de Arcas, G. (2018) · The Science of The Total Environment · doi:10.1016/j.scitotenv.2018.12.071 · Cited by 32
Separating the signal from the noise – Financial machine learning for Twitter
Schnaubelt, M., Fischer, T. G., & Krauß, C. (2020) · Journal of Economic Dynamics and Control · doi:10.1016/j.jedc.2020.103895 · Cited by 39
Ouerhani, N., Maalel, A., Ghézala, H. B., & Chouri, S. (2020) · doi:10.21203/rs.3.rs-33343/v1 · Cited by 32
“However, other works [17,15,20,29,28] have benefited from the power of deep learning sometimes to adjust the sentiment of the chatbot response, and sometimes to detect depression in text sequences.”
BackgroundZhang, S., Gong, H., & She, L. (2023) · Knowledge-Based Systems · doi:10.1016/j.knosys.2023.110662 · Cited by 31
The hybrid of BERT and deep learning models for Indonesian sentiment analysis
Mandhasiya, D. G., Murfi, H., & Bustamam, A. (2024) · Indonesian Journal of Electrical Engineering and Computer Science · doi:10.11591/ijeecs.v33.i1.pp591-602 · Cited by 24
“Research from [18] used the CNN-LSTM hybrid model for sentiment analysis in English.”
BackgroundMethod
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.