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 401–500 of 1,003
Feature-enhanced attention network for target-dependent sentiment classification
Yang, M., Qu, Q., Chen, X., Guo, C., Shen, Y., & Lei, K. (2018) · Neurocomputing · doi:10.1016/j.neucom.2018.04.042 · Cited by 55
“[5] proposed an attention-based LSTM method to learn an aspect embedding for each aspect and made aspects participate in computing attention weights.”
BackgroundMethodInfluentialFernández, J., Chiachío, J., Barros, J., Chiachío, M., & Kulkarni, C. S. (2023) · Reliability Engineering & System Safety · doi:10.1016/j.ress.2023.109822 · Cited by 58
Yang, J., Xu, M., Xiao, Y., & Du, X. (2024) · Neurocomputing · doi:10.1016/j.neucom.2023.127222 · Cited by 55
RDGCN: Reinforced Dependency Graph Convolutional Network for Aspect-based Sentiment Analysis
Zhao, X., Peng, H. M., Dai, Q., Bai, X., Peng, H., Liu, Y., Guo, Q., & Yu, P. S. (2024) · ACM International Conference on Web Search and Data Mining (WSDM) · doi:10.1145/3616855.3635775 · Cited by 67
“Since context words in a sentence may have different importance for a given aspect, attention mechanisms are widely integrated in recurrent neural networks [15, 31], memory networks [23], gated networks [33, 37], and convolutional networks [33], etc.”
BackgroundMethodMicroblog sentiment analysis using social and topic context
Zou, X., Yang, J., & Zhang, J. (2018) · PLoS ONE · doi:10.1371/journal.pone.0191163 · Cited by 52
Wang, F., Lan, M., & Wan, M. (2018) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn.2018.8489042 · Cited by 59
“Wang et al. (2016) [14] presented a model for aspect and opinion terms co-extraction.”
BackgroundMethodEffective Attention Networks for Aspect-level Sentiment Classification
Nguyen, H. T., & Nguyen, L.-M. (2018) · International Conference on Knowledge and Systems Engineering/Proceedings · doi:10.1109/kse.2018.8573324 · Cited by 63
“However, ATAE-LSTM appends aspect embeddings with each word embedding to present the context [17].”
BackgroundMethodShuang, K., Ren, X., Yang, Q., Li, R., & Loo, J. (2018) · Neurocomputing · doi:10.1016/j.neucom.2018.11.084 · Cited by 53
“AE-LSTM integrated the Aspect Embedding information in the input of LSTM, AT-LSTM integrated the Attention Mechanism in the hidden state of LSTM to capture the key part of sentence in response to a given aspect and ATAE-LSTM was formed by the combination of AE-LSTM and AT-LSTM [14].”
BackgroundMethodInfluentialQiu, Q., Xie, Z., Wu, L., & Tao, L. (2020) · Earth and Space Science · doi:10.1029/2019ea000993 · Cited by 57
“• AT‐LSTM (Wang et al., 2016): LSTM network with attention mechanism; hence, the model can focus on the key and important parts in the sentence.”
BackgroundMethodInfluentialA novel category detection of social media reviews in the restaurant industry
Khan, M. U., Javed, A. R., Ihsan, M., & Tariq, U. (2020) · Multimedia Systems · doi:10.1007/s00530-020-00704-2 · Cited by 60
“[41] introduced in which the author revealed that the sentence polarity is not only related to the content, but it is also based upon the essential aspect.”
BackgroundA multi-head neural network with unsymmetrical constraints for remaining useful life prediction
Liu, Z., Liu, H., Jia, W., Zhang, D., & Tan, J. (2021) · Advanced Engineering Informatics · doi:10.1016/j.aei.2021.101396 · Cited by 52
Xu, L., Pang, X., Wu, J., Cai, M., & Peng, J. (2022) · Neurocomputing · doi:10.1016/j.neucom.2022.10.071 · Cited by 54
Zhang, H., Cheah, Y., Alyasiri, O. M., & An, J. (2024) · Artificial Intelligence Review · doi:10.1007/s10462-023-10633-x · Cited by 62
SarcasmBench: Towards Evaluating Large Language Models on Sarcasm Understanding
Zhang, Y., Zou, C., Lian, Z., Tiwari, P., & Qin, J. (2025) · IEEE Transactions on Affective Computing · doi:10.1109/taffc.2025.3604806 · Cited by 67
“Sarcasm in this dataset is usually embedded indirectly within extended argumentative discourse, requiring the model to track inter-sentential cues and pragmatic implications.”
Park, H.-J., Song, M., & Shin, K.-S. (2019) · Knowledge-Based Systems · doi:10.1016/j.knosys.2019.06.033 · Cited by 53
Recent advances in deep learning based sentiment analysis
Yuan, J., Wu, Y., Lu, X., Zhao, Y., Qin, B., & Liu, T. (2020) · Science China Technological Sciences · doi:10.1007/s11431-020-1634-3 · Cited by 52
S2SAN: A sentence-to-sentence attention network for sentiment analysis of online reviews
Wang, P. Q., Li, J., & Hou, J. (2021) · Decision Support Systems · doi:10.1016/j.dss.2021.113603 · Cited by 55
Bert-Enhanced Text Graph Neural Network for Classification
Yang, Y., & Cui, X. (2021) · Entropy · doi:10.3390/e23111536 · Cited by 59
“The attention mechanism is applied to various models, greatly improving the performance of various NLP tasks [19].”
MethodContext-aware Embedding for Targeted Aspect-based Sentiment Analysis
Liang, B., Du, J., Xu, R., Li, B., & Huang, H. (2019) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/p19-1462 · Cited by 50
“Recently, attention-based neural models achieve remarkable success in ABSA (Fan et al., 2018; Wang et al., 2016; Tang et al., 2016).”
BackgroundEnhancing Aspect-Based Sentiment Analysis With Capsule Network
Su, J., Yu, S., & Luo, D. (2020) · IEEE Access · doi:10.1109/access.2020.2997675 · Cited by 54
Das, S., & Kolya, A. K. (2021) · Evolutionary Intelligence · doi:10.1007/s12065-021-00598-7 · Cited by 53
“Meanwhile, though the RNN-LSTM models were churn-ing out quite fair and accurate results for the textual experiments [36], one major problem with this model is their backpropagation feedback-per cycle system [37].”
MethodDual-Perspective Fusion Network for Aspect-Based Multimodal Sentiment Analysis
Wang, D., Tian, C., Xiao, L., Zhao, L., He, L., & Wang, Q. (2023) · IEEE Transactions on Multimedia · doi:10.1109/tmm.2023.3321435 · Cited by 51
“Furthermore, transformer-based models are often used in fine-grained sentiment analysis methods [29], [30], [31], [32] to extract information related to aspect terms from text.”
MethodSelf-citationImproving Attention Model Based on Cognition Grounded Data for Sentiment Analysis
Long, Y., Xiang, R., Lu, Q., Huang, C., & Li, M. (2019) · IEEE Transactions on Affective Computing · doi:10.1109/taffc.2019.2903056 · Cited by 55
“In [85], different lexicons were used to build attention models.”
MethodSentiment Classification Based on Part-of-Speech and Self-Attention Mechanism
Cheng, K., Yue, Y., & Song, Z. (2020) · IEEE Access · doi:10.1109/access.2020.2967103 · Cited by 52
“[43] proposed an Attention-based Long Short-Term Memory Network for aspect-level sentiment classification.”
MethodSpatiotemporal saliency-based multi-stream networks with attention-aware LSTM for action recognition
Liu, Z., Li, Z., Wang, R., Zong, M., & Ji, W. (2020) · Neural Computing and Applications · doi:10.1007/s00521-020-05144-7 · Cited by 52
“Recurrent neural networks, especially LSTM networks, are widely applied to many tasks such as text generation, machine translation and speech recognition [3, 26, 34, 44, 53].”
BackgroundEnhancing Aspect-level Sentiment Analysis with Word Dependencies
Tian, Y., Chen, G., & Song, Y. (2021) · Conference of the European Chapter of the Association for Computational Linguistics · doi:10.18653/v1/2021.eacl-main.326 · Cited by 60
“, 2014) followed the sentence classification paradigm and recent studies enhanced it as a mission of sentenceaspect pair classification with applying neural approaches (Wang et al., 2016; Tang et al., 2016a; Ma et al., 2017; Chen et al., 2017; Xue and Li, 2018; Li et al., 2018b; Hu et al., 2019; Xu et al., 2019) such…”
BackgroundInfluentialTo be Closer: Learning to Link up Aspects with Opinions
Zhou, Y., Liao, L., Gao, Y., Jie, Z., & Lu, W. (2021) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2021.emnlp-main.317 · Cited by 60
“Early efforts on aspect-based sentiment focused on predicting polarity by employing attention mechanism (Bah-danau et al., 2015) to model interactions between aspect and context words (Wang et al., 2016; Chen et al., 2017; Liu and Zhang, 2017; Li et al., 2018; Wang et al., 2018).”
BackgroundCross-modal complementary network with hierarchical fusion for multimodal sentiment classification
Peng, C., Zhang, C., Xue, X., Gao, J., Liang, H., & Niu, Z. (2021) · Tsinghua Science & Technology · doi:10.26599/tst.2021.9010055 · Cited by 50
Multi-Entity Aspect-Based Sentiment Analysis With Context, Entity and Aspect Memory
Yang, J., Yang, R., Wang, C., & Xie, J. (2018) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v32i1.12059 · Cited by 53
“As ATAE-LSTM proposed in (Wang et al. 2016) only deals with aspect part, we add entity part in the same manner as aspect.”
BackgroundMethodInfluentialImproving aspect-based sentiment analysis via aligning aspect embedding
Tan, X., Cai, Y., Xu, J., Leung, H.-F., Chen, W., & Li, Q. (2019) · Neurocomputing · doi:10.1016/j.neucom.2019.12.035 · Cited by 51
Zheng, Y., Zhang, R., Mensah, S., & Mao, Y. (2020) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v34i05.6517 · Cited by 55
“Recurrent Neural Networks (RNNs), equipped with attention mechanism and memory module, is the most commonly used technique for ALSC (Wang et al. 2016b; Tang, Qin, and Liu 2016; Ma et al. 2017; Chen et al. 2017).”
MethodTasty Burgers, Soggy Fries: Probing Aspect Robustness in Aspect-Based Sentiment Analysis
Xing, X., Jin, Z., Jin, D., Wang, B., Zhang, Q., & Huang, X. (2020) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2020.emnlp-main.292 · Cited by 72
Aspect-based sentiment analysis: an overview in the use of Arabic language
Bensoltane, R., & Zaki, T. (2022) · Artificial Intelligence Review · doi:10.1007/s10462-022-10215-3 · Cited by 50
“For the sentiment polarity identification, the authors followed the idea of the ATAE-LSTM model (Wang et al. 2016) by computing attention weights using aspects embedding and word embeddings to improve the results of identifying aspect sentiment polarity.”
MethodAttention based hierarchical LSTM network for context-aware microblog sentiment classification
Feng, S., Wang, Y., Liu, L., Wang, D., & Yu, G. (2018) · World Wide Web · doi:10.1007/s11280-018-0529-6 · Cited by 49
“appended the aspect embedding into input each word vector and the final output of the LSTM network was weighted sum of hidden vectors with the help of global attention mechanism [34].”
BackgroundSelf-citationNeural Attentive Network for Cross-Domain Aspect-Level Sentiment Classification
Yang, M., Yin, W., Qu, Q., Tu, W., Shen, Y., & Chen, X. (2019) · IEEE Transactions on Affective Computing · doi:10.1109/taffc.2019.2897093 · Cited by 51
A Novel Aspect-Guided Deep Transition Model for Aspect Based Sentiment Analysis
Liang, Y., Meng, F., Zhang, J., Xu, J., Chen, Y., & Zhou, J. (2019) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/d19-1559 · Cited by 54
“Meanwhile, we also conduct a three-class experiment, in order to compare with some work (Wang et al., 2016; Ma et al., 2017; Li et al., 2018a) which removed “conflict” labels.”
BackgroundMethodYou, L., Han, F., Peng, J., Jin, H., & Claramunt, C. (2022) · Knowledge-Based Systems · doi:10.1016/j.knosys.2022.109511 · Cited by 53
Sadr, H., & Soleimandarabi, M. N. (2022) · The Journal of Supercomputing · doi:10.1007/s11227-021-04208-2 · Cited by 51
“[38] proposed a domain attention model for multi-domain sentiment analysis that employed domain representation as attention to choose the most suitable domain-related features in each domain.”
BackgroundSpatio temporal hydrological extreme forecasting framework using LSTM deep learning model
Anshuka, A., Chandra, R., Buzacott, A., Sanderson, D., & van Ogtrop, F. (2022) · Stochastic Environmental Research and Risk Assessment · doi:10.1007/s00477-022-02204-3 · Cited by 50
“LSTM networks have recently been further improved with the emergence of bidirectional LSTM (Huang et al. 2015), encoder-decoder LSTM (Cho et al. 2014), attention LSTM (Wang et al. 2016) and transformer LSTM models (Sun et al. 2021).”
BackgroundDeep Learning Models for Predicting Gas Adsorption Capacity of Nanomaterials
Guo, W., Liu, J., Dong, F., Chen, R., Das, J., Ge, W., Xu, X., & Hong, H. (2022) · Nanomaterials · doi:10.3390/nano12193376 · Cited by 57
“LSTM is an advanced recurrent neural network and has been widely used for natural language processing due to its ability to deal with sequential data [47,48].”
BackgroundBreaking down linguistic complexities: A structured approach to aspect-based sentiment analysis
Ahmed, K., Nadeem, M. I., Zheng, Z., Li, D., Ullah, I., Assam, M., Ghadi, Y. Y., & Mohamed, H. G. (2023) · Journal of King Saud University - Computer and Information Sciences · doi:10.1016/j.jksuci.2023.101651 · Cited by 59
“However, these approaches inadvertently neglected the incorporation of essential syntactic information (Wang et al., 2016; Huang and Carley, 2019).”
InfluentialAspect-based sentiment classification with aspect-specific hypergraph attention networks
Ouyang, J., Xuan, C., Wang, B., & Yang, Z. (2024) · Expert Systems with Applications · doi:10.1016/j.eswa.2024.123412 · Cited by 54
On Tree-Based Neural Sentence Modeling
Shi, H., Zhou, H., Chen, J., & Li, L. (2018) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/d18-1492 · Cited by 52
“We do not include any attention (Wang et al., 2016; Lin et al., 2017) or pooling (Collobert and Weston, 2008; Socher et al., 2011; Zhou et al., 2016b) mechanism here, in order to avoid distractions and make the encoder structure affects the most.”
BackgroundFeature distillation network for aspect-based sentiment analysis
Shuang, K., Yang, Q., Loo, J., Li, R., & Gu, M. (2020) · Information Fusion · doi:10.1016/j.inffus.2020.03.003 · Cited by 49
Two-Level LSTM for Sentiment Analysis With Lexicon Embedding and Polar Flipping
Wu, O., Yang, T., Li, M., & Li, M. (2020) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2020.3017378 · Cited by 53
Mining and classifying customer reviews: a survey
Subhashini, L., Li, Y., Zhang, J., Atukorale, A. S., & Wu, Y. (2021) · Artificial Intelligence Review · doi:10.1007/s10462-021-09955-5 · Cited by 51
“However, researchers have pointed out the disadvantages of existing deep learning models (Li and Chen 2014; Vateekul and Koomsubha 2016) and attention models (Shin et al. 2016; He et al. 2018; Lei et al. 2018; Wang et al. 2016).”
BackgroundEmbedding Refinement Framework for Targeted Aspect-Based Sentiment Analysis
Liang, B., Yin, R., Du, J., Gui, L., He, Y., Yang, M., & Xu, R. (2021) · IEEE Transactions on Affective Computing · doi:10.1109/taffc.2021.3071388 · Cited by 47
“ATAE-LSTM [43]: An attention-based bidirectional LSTM model, which incorporates the aspect information based on the attention mechanism.”
BackgroundMethodInfluentialEnhancing Aspect-Based Sentiment Analysis with Supervised Contrastive Learning
Liang, B., Luo, W., Li, X., Gui, L., Yang, M., Yu, X., & Xu, R. (2021) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3459637.3482096 · Cited by 61
“Following previous ABSA works [8, 29], we perform Accuracy metric to measure the performance of the models.”
MethodDynamic commonsense knowledge fused method for Chinese implicit sentiment analysis
Liao, J., Wang, M., Chen, X., Wang, S., & Zhang, K. (2022) · Information Processing & Management · doi:10.1016/j.ipm.2022.102934 · Cited by 53
A novel weight-oriented graph convolutional network for aspect-based sentiment analysis
Yu, B., & Zhang, S. (2022) · The Journal of Supercomputing · doi:10.1007/s11227-022-04689-9 · Cited by 51
Aspect-level sentiment analysis based on semantic heterogeneous graph convolutional network
Zeng, Y., Li, Z., Chen, Z., & Ma, H. (2023) · Frontiers of Computer Science · doi:10.1007/s11704-022-2256-5 · Cited by 56
Aspect-Based Sentiment Analysis using Machine Learning and Deep Learning Approaches
Kumar, D., Gupta, A., Gupta, V. K., & Gupta, A. (2023) · International Journal on Recent and Innovation Trends in Computing and Communication · doi:10.17762/ijritcc.v11i5s.6636 · Cited by 46
Flexibly utilizing syntactic knowledge in aspect-based sentiment analysis
Huang, X., Li, J., Wu, J. X., Chang, J., Liu, D., & Zhu, K. (2024) · Information Processing & Management · doi:10.1016/j.ipm.2023.103630 · Cited by 55
Hybrid Deep Learning Models for Thai Sentiment Analysis
Pasupa, K., & Ayutthaya, T. S. N. (2021) · Cognitive Computation · doi:10.1007/s12559-020-09770-0 · Cited by 48
“…use convolutional neural network (CNN), the prevailing algorithm for computer vision and text analysis, to extract local structure while resorting to long short-term memory (LSTM) and bi-directional LSTM (BLSTM) to manage sequential data and various linguistic patterns, respectively [5–7].”
BackgroundMethodEnd-to-end aspect-based sentiment analysis with hierarchical multi-task learning
Wang, X., Xu, G., Zhang, Z., Jin, L., & Sun, X. (2021) · Neurocomputing · doi:10.1016/j.neucom.2021.03.100 · Cited by 51
Sentiment analysis using novel and interpretable architectures of Hidden Markov Models
Perikos, I., Kardakis, S., & Hatzilygeroudis, I. (2021) · Knowledge-Based Systems · doi:10.1016/j.knosys.2021.107332 · Cited by 50
A Robustly Optimized BMRC for Aspect Sentiment Triplet Extraction
Liu, S., Li, K., & Li, Z. (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.20 · Cited by 46
“ABSA includes three basic subtasks: aspect term extraction (Yin et al., 2016; Li et al., 2018; Ma et al., 2019), opinion term extraction (Liu et al., 2015; Wu et al., 2021), and aspect level sentiment classification (Wang et al., 2016; Chen et al., 2017; Jiang et al., 2019; Zhang and Qian, 2020).”
BackgroundLifelong Learning Memory Networks for Aspect Sentiment Classification
Wang, S., Lv, G., Mazumder, S., Fei, G., & Liu, B. (2018) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata.2018.8622304 · Cited by 49
“SemEval 2014 [34] is a benchmark dataset that has been used in related studies [2], [3].”
BackgroundMethodInfluentialYang, M., Jiang, Q., Shen, Y., Wu, Q., Zhao, Z., & Zhou, W. (2019) · Neural Networks · doi:10.1016/j.neunet.2019.05.021 · Cited by 47
Transformer Based Memory Network for Sentiment Analysis of Web Comments
Jiang, M., Wu, J., Shi, X., & Zhang, M. (2019) · IEEE Access · doi:10.1109/access.2019.2957192 · Cited by 50
“Reference [23] combines the attention mechanism with LSTM.”
An adversarial bidirectional serial–parallel LSTM-based QTD framework for product quality prediction
Liu, Z., Zhang, D., Jia, W., Lin, X., & Liu, H. (2020) · Journal of Intelligent Manufacturing · doi:10.1007/s10845-019-01530-8 · Cited by 47
“Bi-LSTM is a widely used model for processing words with relatively long intervals and delays (Wang et al. 2016; Peters et al. 2018).”
MethodEvent prediction based on evolutionary event ontology knowledge
Mao, Q., Li, X., Peng, H. M., Li, J., He, D., Guo, S., He, M., & Wang, L. (2020) · Future Generation Computer Systems · doi:10.1016/j.future.2020.07.041 · Cited by 45
GRACE: Gradient Harmonized and Cascaded Labeling for Aspect-based Sentiment Analysis
Luo, H., Ji, L., Li, T., Jiang, D., & Duan, N. (2020) · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · doi:10.18653/v1/2020.findings-emnlp.6 · Cited by 58
Semantics-Preserved Data Augmentation for Aspect-Based Sentiment Analysis
Hsu, T.-W., Chen, C.-C., Huang, H., & Chen, H. (2021) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2021.emnlp-main.362 · Cited by 62
“Wang et al. (2016) propose an attention-based LSTM, which can concentrate on distinct parts of a sentence by calculating the corresponding attention weights, to learn aspect embedding.”
BackgroundResidual attention and other aspects module for aspect-based sentiment analysis
Wu, C., Xiong, Q., Yang, Z., Gao, M., Li, Q., Yu, Y., Wang, K., & Zhu, Q. (2021) · Neurocomputing · doi:10.1016/j.neucom.2021.01.019 · Cited by 46
Enhanced Aspect Level Sentiment Classification with Auxiliary Memory.
Zhu, P., & Qian, T. (2018) · International Conference on Computational Linguistics · Cited by 57
A Target-Guided Neural Memory Model for Stance Detection in Twitter
Wei, P., Mao, W., & Zeng, D. D. (2018) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn.2018.8489665 · Cited by 52
“However, compared with SVM, both AT-biGRU and TAN perform worse than it, demonstrating that adding attention mechanism into neural architectures for stance detection in the similar way to ABSA models like [30] is not particularly efficient.”
MethodMulti-layer Attention Based CNN for Target-Dependent Sentiment Classification
Zhang, S., Xu, X., Pang, Y., & Han, J. (2019) · Neural Processing Letters · doi:10.1007/s11063-019-10017-9 · Cited by 49
“ATAE-LSTM performs better than TD-LSTM, mainly because the attention mechanism can capture the sentiment information corresponding to the target and achieve the information interaction from the target to the context.”
BackgroundInfluentialA multi-view CNN-based acoustic classification system for automatic animal species identification
Xu, W., Zhang, X., Yao, L., Xue, W., & Wei, B. (2020) · Ad Hoc Networks · doi:10.1016/j.adhoc.2020.102115 · Cited by 44
“The application of deep learning in audio signal is not new; however, most previous studies focus on human speech analysis to obtain context information [19, 20, 22].”
BackgroundChrysostomou, G., & Αλέτρας, Ν. (2021) · doi:10.18653/v1/2021.acl-long.40 · Cited by 69
“…explanations for a given prediction and qualitative model analysis by assigning importance to input tokens using scores provided by attention mechanisms (Chen et al., 2017; Wang et al., 2016; Jain et al., 2020; Sun and Lu, 2020) as a mean towards model interpretability (Lipton, 2016; Miller, 2017).”
MethodZhang, X., Kuenzel, S., Colombo, N., & Watkins, C. (2022) · Journal of Modern Power Systems and Clean Energy · doi:10.35833/mpce.2021.000276 · Cited by 43
“mary to the input sequence, which reduces the model perfor‐ mance [46].”
BackgroundSentiment Classification by Leveraging the Shared Knowledge from a Sequence of Domains
Lv, G., Wang, S., Liu, B., Chen, E., & Zhang, K. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-18576-3_47 · Cited by 46
“Many aspect-based sentiment analysis methods are also reported [5,14,17,26,33,36,37,39].”
MethodDualGCN: Exploring Syntactic and Semantic Information for Aspect-Based Sentiment Analysis
Li, R., Chen, H., Feng, F., Ma, Z., Wang, X., & Hovy, E. H. (2022) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2022.3219615 · Cited by 51
“1) The first seven methods are the attention-based models. a) ATAE-LSTM [17] combines the aspect embedding with all the input word embeddings in a sentence, and then input them into LSTM.”
BackgroundMethodInfluentialSyntactic Graph Attention Network for Aspect-Level Sentiment Analysis
Li, Y., Wang, J., Yu, L.-C., & Zhang, X. (2022) · IEEE Transactions on Artificial Intelligence · doi:10.1109/tai.2022.3227535 · Cited by 46
A Survey of Quantum-cognitively Inspired Sentiment Analysis Models
Liu, Y., Li, Q., Wang, B., Zhang, Y., & Song, D. (2023) · ACM Computing Surveys · doi:10.1145/3604550 · Cited by 49
Huang, W., Gao, T., Hao, Y., & Wang, X. (2023) · Energy Economics · doi:10.1016/j.eneco.2023.107106 · Cited by 43
Enhancing aspect-based sentiment analysis with BERT-driven context generation and quality filtering
Zhao, C., Feng, R., Sun, X., Shen, L., Gao, J., & Wang, Y. (2024) · Natural Language Processing Journal · doi:10.1016/j.nlp.2024.100077 · Cited by 52
Self-citationSurvey on Classic and Latest Textual Sentiment Analysis Articles and Techniques
Shi, Y., Zhu, L., Li, W., Guo, K., & Zheng, Y. (2019) · International Journal of Information Technology & Decision Making · doi:10.1142/s0219622019300015 · Cited by 77
Sentiment Analysis With Comparison Enhanced Deep Neural Network
Lin, Y., Li, J., Yang, L., Xu, K., & Lin, H. (2020) · IEEE Access · doi:10.1109/access.2020.2989424 · Cited by 43
“Wang et al. [13] proposed an Attention-based Long Short-Term Memory Network for aspect-level sentiment classification.”
BackgroundExploring Interpretable Predictive Models for Business Processes
Sindhgatta, R., Moreira, C., Ouyang, C., & Barros, A. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-58666-9_15 · Cited by 55
“Current studies in the literature have used attention-based models mainly in Natural Language Processing tasks [17, 6, 4].”
MethodKnowledge-Guided Sentiment Analysis Via Learning From Natural Language Explanations
Ke, Z., Sheng, J., Li, Z., Silamu, W., & Guo, Q. (2021) · IEEE Access · doi:10.1109/access.2020.3048088 · Cited by 46
“(3) ATAE-LSTM [40] incorporates the aspect term information into both embedding layer and attention layer to help the model concentrate on different parts of a sentence.”
BackgroundAspect-Level Sentiment Analysis Based on Bidirectional-GRU in SIoT
Ali, W., Yang, Y., Qiu, X., Ke, Y., & Wang, Y. (2021) · IEEE Access · doi:10.1109/access.2021.3078114 · Cited by 43
“To obtain attention vectors, they use the embedding of aspect words in order to demonstrate the context and construct attention vector, ATAE-LSTM integrates embedding of aspect and word embedding vector [43].”
MethodSelf-citationAspect-based sentiment analysis with component focusing multi-head co-attention networks
Cheng, L., Chen, Y., & Liao, Y.-Y. (2022) · Neurocomputing · doi:10.1016/j.neucom.2022.03.027 · Cited by 46
Wang, Q., Xu, H., Wen, Z., Liang, B., Yang, M., Qin, B., & Xu, R. (2023) · IEEE Transactions on Affective Computing · doi:10.1109/taffc.2023.3333200 · Cited by 53
CABiLSTM-BERT: Aspect-based sentiment analysis model based on deep implicit feature extraction
He, B., Zhao, R., & Tang, D. (2024) · Knowledge-Based Systems · doi:10.1016/j.knosys.2024.112782 · Cited by 48
Brush like a Dentist: Accurate Monitoring of Toothbrushing via Wrist-Worn Gesture Sensing
Luo, C., Feng, X., Chen, J., Li, J., Xu, W., Li, W., Zhang, L., Tari, Z., & Zomaya, A. Y. (2019) · IEEE Conference on Computer Communications (INFOCOM) · doi:10.1109/infocom.2019.8737513 · Cited by 50
“We conduct the following operations to acquire the representation of the toothbrushing activity [24]:”
BackgroundMethodInfluentialMining Significant Microblogs for Misinformation Identification: An Attention-Based Approach
Liu, Q., Yu, F. N., Wu, S., & Wang, L. (2018) · ACM Transactions on Intelligent Systems and Technology · doi:10.1145/3173458 · Cited by 51
“h as possible. The attention mechanism has succeed in multiple tasks, such as visual object detection [1], image caption [39], machine translation [2], text summarization [33] and text classification [35]. Accordingly, with the attention mechanism, we are able to mine signification microblogs for identifying misinform…”
MethodTargeted Sentiment Classification Based on Attentional Encoding and Graph Convolutional Networks
Xiao, L., Hu, X., Chen, Y., Xue, Y., Gu, D., Chen, B., & Zhang, T. (2020) · Applied Sciences · doi:10.3390/app10030957 · Cited by 44
“In later studies, various neural-network-based methods became popular [6,7], which did not need manual feature engineering.”
MethodBi-directional LSTM–CNN Combined method for Sentiment Analysis in Part of Speech Tagging (PoS)
Kumar, N. K. S., & Malarvizhi, N. (2020) · International Journal of Speech Technology · doi:10.1007/s10772-020-09716-9 · Cited by 42
“There are different LSTM based Models (Wang et al. 2016), which are successfully used to classify the text in sentiment analysis.”
MethodImproving aspect-level sentiment analysis with aspect extraction
Majumder, N., Bhardwaj, R., Poria, S., Gelbukh, A. F., & Hussain, A. (2020) · Neural Computing and Applications · doi:10.1007/s00521-020-05287-7 · Cited by 50
“[7, 8] proposed few of the neural network-based method for ALSA.”
BackgroundMethodEnsemble deep learning for aspect-based sentiment analysis
Mohammadi, A., & Shaverizade, A. (2021) · International journal of nonlinear analysis and applications · doi:10.22075/ijnaa.2021.4769 · Cited by 70
“Wang et al. [18] proposed an Attention-based Long Short-Term Memory (LSTM) model for aspect-based sentiment analysis.”
MethodRAIN: Reinforced Hybrid Attention Inference Network for Motion Forecasting
Li, J., Yang, F., Ma, H., Malla, S., Tomizuka, M., & Choi, C. (2021) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv48922.2021.01579 · Cited by 42
“Existing works have demonstrated the superiority of attention in a broad range of domains, such as natural language processing [43, 47, 57], image captioning [2, 56, 63], saliency detection [33, 64], time-series modeling [10, 45], human activity recognition [6,48,49].”
BackgroundText classification of Chinese news based on multi-scale CNN and LSTM hybrid model
Zhai, Z., Zhang, X., Fang, F., & Yao, L. (2023) · Multimedia Tools and Applications · doi:10.1007/s11042-023-14450-w · Cited by 42
“References [16, 18] proposed a method of adding attention mechanism, and achieved excellent classification effect.”
MethodMurugaiyan, S., & Reddy, U. S. (2023) · Cognitive Computation · doi:10.1007/s12559-023-10127-6 · Cited by 45
“Kwon (2021) [56] Spatial features and temporal features 1D-DCNN IEMOCAP 73.”
BackgroundMethodWang, P., Tao, L., Tang, M., Wang, L., Xu, Y., & Zhao, M. (2024) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2024.108101 · Cited by 51
Deep learning-assisted high-resolution sonar detection of local damage in underwater structures
Tan, H., Zheng, L., Ma, C., Xu, Y., & Sun, Y. (2024) · Automation in Construction · doi:10.1016/j.autcon.2024.105479 · Cited by 43
Alam, M. S., Mrida, M. S. H., & Rahman, M. A. (2025) · American Journal of Scholarly Research and Innovation · doi:10.63125/r3sq6p80 · Cited by 62
Review-aggregated aspect-based sentiment analysis with ontology features
de Kok, S., Punt, L., van den Puttelaar, R., Ranta, K., Schouten, K., & Frăsincar, F. (2018) · Progress in Artificial Intelligence · doi:10.1007/s13748-018-0163-7 · Cited by 46
“Given the current trend in using deep neural networks, it would be interesting to see how methods, such as attention-based LSTMs [23] or dyadic memory networks [22], can be combined with the external knowledge and reasoning from ontologies.”
MethodA Bi-Directional LSTM-CNN Model with Attention for Aspect-Level Text Classification
Zhu, Y., Gao, X., Zhang, W., Liu, S., & Zhang, Y. (2018) · Future Internet · doi:10.3390/fi10120116 · Cited by 41
“Compared to AT-LSTM, its independent attention module has better performance to extract the important parts in the sentence.”
BackgroundMethodInfluentialWang, J., Sun, C., Li, S., Liu, X., Si, L., Zhang, M., & Zhou, G. (2019) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/p19-1345 · Cited by 48
“The baselines are listed as follows in detail: 1) LSTM (Wang et al., 2016).”
BackgroundInfluential
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.