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 801–900 of 1,003
Weng, Y., Chen, X., Chen, L., & Liu, W. P. (2020) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2020.3036212 · Cited by 23
Lu, X., Zhu, Y., Xu, Y., & Yu, J. (2021) · Neurocomputing · doi:10.1016/j.neucom.2020.12.023 · Cited by 21
Pramanick, S., Akhtar, M. S., & Chakraborty, T. (2021) · Proceedings of the International AAAI Conference on Web and Social Media · doi:10.1609/icwsm.v15i1.18080 · Cited by 21
Economic Recession Prediction Using Deep Neural Network
Wang, Z., Li, K., Xia, S. Q., & Liu, H. (2022) · The Journal of Financial Data Science · doi:10.3905/jfds.2022.1.097 · Cited by 21
Bioelectronics for targeted pain management
Flavin, M. T., Foppiani, J., Paul, M. A., Alvarez, A. H., Foster, L., Gavlasova, D., Ma, H., Rogers, J. A., & Lin, S. J. (2025) · Nature Reviews Electrical Engineering · doi:10.1038/s44287-025-00177-3 · Cited by 20
“Supervised learning techniques for classifying linguistic and visual inputs, such as deep learning 85 and long short-term memory networks 86 , enable specific emotions to be identified.”
LSTM Network based Sentiment Analysis for Customer Reviews
BİLEN, B., & Horasan, F. (2021) · Journal of Polytechnic · doi:10.2339/politeknik.844019 · Cited by 20
A Hybrid Approach of Opinion Mining and Comparative Linguistic Analysis of Restaurant Reviews
Sazzed, S. (2021) · International conference Recent advances in natural language processing · doi:10.26615/978-954-452-072-4_144 · Cited by 20
A Deep Learning Neural Network for the Residential Energy Consumption Prediction
Huang, J., Pang, C., Yang, W., Zeng, X., Zhang, J., & Huang, C. (2022) · IEEJ Transactions on Electrical and Electronic Engineering · doi:10.1002/tee.23543 · Cited by 22
Imbalanced Text Sentiment Classification Based on Multi-Channel BLTCN-BLSTM Self-Attention
Cai, T., & Zhang, X. (2023) · Sensors · doi:10.3390/s23042257 · Cited by 20
“[29] introduced the self‐attentionmechanism and aspect word embedding into the traditional LSTM model, which divides the sentiment of”
BackgroundTarget-oriented multimodal sentiment classification by using topic model and gating mechanism
Song, Z., Xue, Y., Gu, D., Zhang, H., & Ding, W. (2023) · International Journal of Machine Learning and Cybernetics · doi:10.1007/s13042-022-01757-7 · Cited by 20
“Seeing that a person’s sentiments considerably impacts the intended content [3], the sentiment analysis of social media posts plays a pivot role in comprehending the conveyed opinions.”
BackgroundAspect-Based Sentiment Analysis with Dependency Relation Weighted Graph Attention
Jiang, T., Wang, Z., Yang, M., & Li, C. (2023) · Information · doi:10.3390/info14030185 · Cited by 24
“[8] proposed an attention-based LSTM (ATAE-LSTM) model using target embeddings, where the context and aspectual word splicing is fed into the LSTM for encoding, and the encoded vector is spliced with the aspectual word vector to obtain the sentiment category by computing through the attention mechanism.”
MethodInfluentialS 3 map: Semisupervised aspect-based sentiment analysis with masked aspect prediction
Yang, Z., Wang, B., Li, X., Wan, M., & Ouyang, J. (2023) · Knowledge-Based Systems · doi:10.1016/j.knosys.2023.110513 · Cited by 21
Yu, H., Zhou, X., Wang, G., Feng, Y., Zhao, H. J., & Wang, J. (2023) · Neurocomputing · doi:10.1016/j.neucom.2023.126462 · Cited by 20
Guan, M., Li, F., & Xue, Y. (2023) · IEEE Transactions on Computational Social Systems · doi:10.1109/tcss.2023.3296476 · Cited by 24
“Previous studies [1], [2], [3], [4] generally integrate the recurrent neural network or its variants with attention mechanisms to set connections between the aspect and its contexts, which achieve satisfying working performance [5].”
BackgroundEmploying synthetic data for addressing the class imbalance in aspect-based sentiment classification
Ganganwar, V., & Rajalakshmi, R. (2023) · Journal of Information and Telecommunication · doi:10.1080/24751839.2023.2270824 · Cited by 28
“TD-LSTM (D. Tang et al., 2015) and ATAE-LSTM (Y. Wang, Huang, et al., 2016) are examples of LSTM-based models.”
BackgroundAspect opinion expression and rating prediction via LDA–CRF hybrid
Laddha, A., & Mukherjee, A. (2018) · Natural Language Engineering · doi:10.1017/s135132491800013x · Cited by 20
“Also, related are the works around aspect-based sentiment classification (Tang et al. 2015; Tang, Qin and Liu 2016; Wang et al. 2016) and the work in Nguyen and Shirai (2015) which proposed an extension of Recurrent Neural Network that takes both dependency and constituent trees of a sentence into…”
BackgroundMethodInfluentialReading Turn by Turn: Hierarchical Attention Architecture for Spoken Dialogue Comprehension
Liu, Z., & Chen, N. F. (2019) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/p19-1543 · Cited by 21
“We concatenate each step of H c with the question h q as in aspect-modeling (Wang et al., 2016), then obtain the question-aware modeling H via a Bi-LSTM layer.”
MethodJoint Learning for Aspect Category Detection and Sentiment Analysis in Chinese Reviews
Zeng, Z., Ma, J., Chen, M., & Li, X. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-31624-2_9 · Cited by 21
Neural Review Rating Prediction with User and Product Memory
Yuan, Z., Wu, F., Liu, J., Wu, C., Huang, Y., & Xie, X. (2019) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3357384.3358138 · Cited by 20
“Inspired by the great success of deep learning, neural network based models have been widely used in sentiment classification [2, 5, 10, 13, 16].”
Recent Trends and Advances in Deep Learning-Based Sentiment Analysis
Ahmet, A., & Abdullah, T. (2020) · Algorithms for intelligent systems · doi:10.1007/978-981-15-1216-2_2 · Cited by 23
SigmaLaw-ABSA: Dataset for Aspect-Based Sentiment Analysis in Legal Opinion Texts
Mudalige, C. R., Karunarathna, D., Rajapaksha, I., de Silva, N., Ratnayaka, G., Perera, A. S., & Pathirana, R. (2020) · IEEE International Conference on Industrial and Information Systems (ICIIS) · doi:10.1109/iciis51140.2020.9342650 · Cited by 20
“• Attention-based LSTM (AT-LSTM) [24] - This model uses an LSTM network with an attention mechanism to incorporate the interaction among words and the target.”
BackgroundMethodInfluentialAspect-Based Sentiment Analysis Using Graph Convolutional Networks and Co-attention Mechanism
Chen, Z., Xue, Y., Xiao, L., Chen, J., & Zhang, H. (2021) · Communications in computer and information science · doi:10.1007/978-3-030-92310-5_51 · Cited by 22
Deep Learning Techniques for Humor Detection in
Sane, S. R., Tripathi, S., Sane, K. R., & Mamidi, R. (2019) · Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis (WASSA) · doi:10.18653/v1/w19-1307 · Cited by 20
“To model these scenarios, we make use of bidirectional LSTM network which has been successfully applied in generating context-dependent hidden representations as well as capturing long-term dependencies in text classification tasks (Wang et al., 2016).”
MethodHierarchical Gated Deep Memory Network With Position-Aware for Aspect-Based Sentiment Analysis
Jia, Z., Bai, X., & Pang, S. (2020) · IEEE Access · doi:10.1109/access.2020.3011318 · Cited by 21
“propose ATAELSTM model [10].”
BackgroundMethodApplying Deep Learning Approach to Targeted Aspect-based Sentiment Analysis for Restaurant Domain
Khine, W. L. K., & Aung, N. T. T. (2019) · International Conference on Advanced Information Technologies (ICAIT) · doi:10.1109/aitc.2019.8920880 · Cited by 19
Emo2Vec: Learning Emotional Embeddings via Multi-Emotion Category
Wang, S., Maoliniyazi, A., Wu, X., & Meng, X. (2020) · ACM Transactions on Internet Technology · doi:10.1145/3372152 · Cited by 32
“Wang et al. [32] combine the word representation and the aspect embedding in the Attention-based LSTM Memory Network for improving the aspect-level sentiment analysis.”
BackgroundXiao-wen, L., Lu, R., Liu, P., & Zhu, Z. (2022) · The Journal of Supercomputing · doi:10.1007/s11227-022-04480-w · Cited by 22
“[21] 2016 SemEval-2014 Attention, LSTM Tang et al.”
MethodLearning Bounded Context-Free-Grammar via LSTM and the Transformer: Difference and the Explanations
Shi, H., Gao, S., Tian, Y., Chen, X., & Zhao, J. (2022) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v36i8.20801 · Cited by 26
A Label-Aware Autoregressive Framework for Cross-Domain NER
Hu, J., Zhao, H., Guo, D., Wan, X., & Chang, T. (2022) · Findings of the Association for Computational Linguistics: NAACL · doi:10.18653/v1/2022.findings-naacl.171 · Cited by 28
Incorporating semantics, syntax and knowledge for aspect based sentiment analysis
Zhao, Z., Tang, M., Zhao, F., Zhang, Z., & Chen, X. (2022) · Applied Intelligence · doi:10.1007/s10489-022-04307-4 · Cited by 22
“• ATAE-LSTM (attention-based LSTM with aspect embedding) [45] appends aspect embedding into each word representation and models the interdependence between words and aspect via attention mechanism.”
MethodXu, J., Yang, S., Xiao, L., Fu, Z., Wu, X., Ma, T., & He, L. (2022) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn55064.2022.9892027 · Cited by 24
“With the emergence of various neural networks, a stream of neural network-based approaches successfully promotes the performance of ASC, including memory-based, long short-term memory (LSTM) based [4], convolution neural networks (CNN) based [5], [6] and hybrid methods [7].”
BackgroundAspect sentiment classification using syntactic neighbour based attention network
Sharma, T., & Kaur, K. (2023) · Journal of King Saud University - Computer and Information Sciences · doi:10.1016/j.jksuci.2023.01.005 · Cited by 19
“3 % and 19.5 % better in terms of F1 score as compared to ATAE-LSTM and ABAE-BiGRU respectively.”
InfluentialA novel adaptive marker segmentation graph convolutional network for aspect-level sentiment analysis
Wang, P., Tao, L., Tang, M., Zhao, M., Wang, L., Xu, Y., Tian, J., & Meng, K. (2023) · Knowledge-Based Systems · doi:10.1016/j.knosys.2023.110559 · Cited by 20
Towards Robust Learning with Noisy and Pseudo Labels for Text Classification
Ahmed, M., Wen, B., Luo, A., Pan, S., Su, J., Cao, X., & Liu, Y. (2024) · Information Sciences · doi:10.1016/j.ins.2024.120160 · Cited by 22
Mamta, M., & Ekbal, A. (2024) · Computer Speech & Language · doi:10.1016/j.csl.2024.101668 · Cited by 22
Deep Interactive Memory Network for Aspect-Level Sentiment Analysis
Sun, C., Lv, L., Tian, G., & Liu, T. (2020) · ACM Transactions on Asian and Low-Resource Language Information Processing · doi:10.1145/3402886 · Cited by 22
“As deep learning is widely used in sentiment analysis, some researchers have proposed effective neural network models to automatically model context and target, and achieve promising results in aspect-level sentimental analysis tasks [9, 10, 18, 19, 22].”
MethodAspect-based sentiment analysis for online reviews with hybrid attention networks
Lin, Y., Fu, Y., Li, Y., Cai, G., & Zhou, A. (2021) · World Wide Web · doi:10.1007/s11280-021-00898-z · Cited by 19
“ATAE-LSTM (Wang et al. 2016 [47]): The attention-based LSTM with aspect embedding (ATAE-LSTM) model considers the aspect as the additional attention information to weights the hidden layer.”
BackgroundMethodInfluentialConCAD: Contrastive Learning-Based Cross Attention for Sleep Apnea Detection
Huang, G., & Ma, F. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-86517-7_5 · Cited by 23
Video emotion analysis enhanced by recognizing emotion in video comments
Cao, W., Zhang, K., Wu, H., Xu, T., Chen, E., Lv, G., & He, M. X. (2022) · International Journal of Data Science and Analytics · doi:10.1007/s41060-022-00317-0 · Cited by 23
“Due to the success of attention mechanisms [11] in computer vision, researchers also introduced this mechanism into text emotion recognition, aiming to improve the performance of this task by the importance of different words in a sentence [33,34].”
BackgroundA weakly-supervised graph-based joint sentiment topic model for multi-topic sentiment analysis
Zhou, T., Law, K. M. Y., & Creighton, D. (2022) · Information Sciences · doi:10.1016/j.ins.2022.07.126 · Cited by 21
Aspect opinion routing network with interactive attention for aspect-based sentiment classification
Yang, B., Han, D., Zhou, R., Gao, D., & Wu, G. (2022) · Information Sciences · doi:10.1016/j.ins.2022.09.051 · Cited by 20
Stacking-Based Ensemble Learning on Low Dimensional Features for Fake News Detection
Li, S., Ma, K., Niu, X., Wang, Y., Ji, K., Yu, Z., & Chen, Z. (2019) · IEEE International Conference on High Performance Computing and Communications; IEEE International Conference on Smart City; IEEE International Conference on Data Science and Systems (HPCC/SmartCity/DSS) · doi:10.1109/hpcc/smartcity/dss.2019.00383 · Cited by 20
Self-citationImamah, I., Husni, H., Rachman, E. M., Suzanti, I. O., & Mufarroha, F. A. (2020) · Journal of Physics Conference Series · doi:10.1088/1742-6596/1477/2/022023 · Cited by 19
“The former aims to identify the aspect and opinion words mentioned in reviews[1][2], while the latter aims to infer the sentiment polarity of specific aspects[3][4].”
BackgroundTransformer-Based Multi-aspect Modeling for Multi-aspect Multi-sentiment Analysis
Wu, Z., Ying, C., Dai, X., Huang, S., & Chen, J. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-60457-8_45 · Cited by 21
“To deal with ABSA, recent works employ neural networks and achieve promising results in previous datasets, such as attention networks [25,16,6], memory networks [22,2], and BERT [9].”
BackgroundMethodInfluentialPars-ABSA: an Aspect-based Sentiment Analysis dataset for PersianPreprint
ataei, T. S., Darvishi, K., Javdan, S., Bidgoli, B. M., & Eetemadi, S. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1908.01815 · Cited by 19
“ATAE-LSTM (Wang et al., 2016): It uses attention mechanism along with Long Short-Term Memory Network.”
MethodGupta, P., & Schütze, H. (2018) · BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP (BlackboxNLP) · doi:10.18653/v1/w18-5418 · Cited by 20
“…2010; Peters et al., 2018), slot filling (Mesnil et al., 2015; Vu et al., 2016b), machine translation (Bahdanau et al., 2014), sentiment analysis (Wang et al., 2016; Tang et al., 2015), semantic textual similarity (Mueller and Thyagarajan, 2016; Gupta et al., 2018a) and dynamic topic modeling…”
BackgroundYu, G., Li, J., Luo, L., Meng, Y., Ao, X., & He, Q. (2021) · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · doi:10.18653/v1/2021.findings-emnlp.115 · Cited by 23
“To name some, Wang et al. (2016a); Li and Lam (2017); Angelidis and Lapata (2018); Ma et al. (2019); Li et al. (2020a); Luo et al. (2019b) came up with different un/supervised methods to solve aspect extraction.”
BackgroundLiu, M., Zhou, F., He, J., Chen, K., Zhao, Y., & Sun, H. (2022) · Soft Computing · doi:10.1007/s00500-022-06793-7 · Cited by 18
“ATAE-LSTM: This model named AT tention-based LSTM for A sp E ct-level sentiment classification, which mainly considered the influences of aspect-specific on every word of text, and then calculated the sum of weighted outputs to denote the final representations ( Wang et al. 2016 ).”
MethodA three-stage neural model for Arabic Dialect Identification
Abdelmajeed, M., Zheng, J., & Ahmed, M. (2023) · Computer Speech & Language · doi:10.1016/j.csl.2023.101488 · Cited by 18
CausalABSC: Causal Inference for Aspect Debiasing in Aspect-Based Sentiment Classification
Zhou, J., Lin, Y., Chen, Q., Zhang, Q., Huang, X., & He, L. (2023) · IEEE/ACM Transactions on Audio Speech and Language Processing · doi:10.1109/taslp.2023.3340606 · Cited by 24
“…inputting it into LSTM; (cid:2) TD-LSTM [18] models the left and right content of the aspect via two independent LSTM models; (cid:2) ATAE-LSTM [19] integrates an attention mechanism into the TC-LSTM model to capture the important words with respect to the given aspect; (cid:2) MEMNET [20]…”
BackgroundMethodYang, H., Zheng-ming, S., Zhao, Y., Liu, J., Wu, Y., & Qin, B. (2024) · Multimedia Tools and Applications · doi:10.1007/s11042-024-18796-7 · Cited by 22
“Multimodal Fine-grained Sentiment Analysis Early works on fine-grained sentiment analysis only focused on text-level [27–31].”
Dual Causes Generation Assisted Model for Multimodal Aspect-Based Sentiment Classification
Fan, R., He, T., Chen, M., Zhang, M., Tu, X., & Dong, M. (2024) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2024.3415028 · Cited by 24
Predicting Stock Price by Using Attention-Based Hybrid LSTM Model
Zhou, J. (2024) · Asian Journal of Basic Science & Research · doi:10.38177/ajbsr.2024.6211 · Cited by 18
Hao, J., Pei, L., He, Y., Xing, Z., & Weng, Y. (2024) · Neurocomputing · doi:10.1016/j.neucom.2024.128163 · Cited by 18
Joint training strategy of unimodal and multimodal for multimodal sentiment analysis
Meng, L., Zhu, Z., Li, K., Zhou, L., Zhao, Z., & Pei, H. (2024) · Image and Vision Computing · doi:10.1016/j.imavis.2024.105172 · Cited by 19
Zhao, C., Kang, L., Sun, X., Xi, X., Shen, L., Gao, J., & Wang, Y. (2025) · IEEE Transactions on Consumer Electronics · doi:10.1109/tce.2025.3563150 · Cited by 18
“…results of the LSTM-based and Attention-based categories in this paper are derived from the study of Huang et al. [30]; the results of BERT-SPC come from the research of Wang et al. [34]; and the results of AEGCN-BERT and IAGCN-BERT are also derived from the study of Bahdanau et al. [32].”
Self-citationSyntax-Directed Hybrid Attention Network for Aspect-Level Sentiment Analysis
Wang, X., Xu, G., Zhang, J., Sun, X., Wang, L., & Huang, T. (2018) · IEEE Access · doi:10.1109/access.2018.2885032 · Cited by 20
“Among all the baseline models, SVM belongs to traditional methods; LSTM and TD-LSTM can be classified into neural network methods; AT-LSTM, HEATB-BIGRU, IAN, AOA-LSTM, BILSTM-ATT, EFFECTIVE-ATT, MemNet, BILSTM-ATT and RAM are part of attention-basedmethods.”
BackgroundMethodInfluentialAspect-Based Sentiment Analysis Using Aspect Map
Noh, Y., Park, S., & Park, S.-B. (2019) · Applied Sciences · doi:10.3390/app9163239 · Cited by 25
“In ATAE-LSTM [22], the aspect vector is concatenated to every word representation, and then an attention mechanism finds proper sentiment expressions of the aspect vector.”
BackgroundMethodInfluentialZero-Shot Multilingual Sentiment Analysis using Hierarchical Attentive Network and BERT
Sarkar, A., Reddy, S., & Iyengar, R. S. (2019) · International Conference on Natural Language Processing and Information Retrieval · doi:10.1145/3342827.3342850 · Cited by 16
“Attention mechanism [20] on LSTM with aspect embedding [21] for document sentiment classification have been tried.”
Mining Purchase Intent in Twitter
Haque, R., Hasanuzzaman, M., Ramadurai, A., & Way, A. (2019) · Computación y Sistemas · doi:10.13053/cys-23-3-3254 · Cited by 18
“Nowadays, RNN, in particular with LSTM [8] hidden units, has been proved to be an effective model for many classification tasks in NLP, e.g. sentiment analysis [19], text classification [11, 21].”
BackgroundWu, C., Wu, F., Liu, J., Huang, Y., & Xie, X. (2019) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3357384.3358086 · Cited by 18
“…LSTM : long-short term memory network [5]; (6) LSTM-Att : LSTM with attention mechanism [15]; (7) ATAE : attention based LSTM with aspect embedding [14]; (8) IAN : LSTM with interactive attention networks [10]; (9) ARP-basic : a variant of our model without aspect-aware review representations;…”
BackgroundCellPred: A Behavior-aware Scheme for Cellular Data Usage Prediction
Zhou, Q., Cao, F., Yang, Y., Wang, S., Liu, Y., Tan, C. W., & Zhang, D. (2020) · Proceedings of the ACM on Interactive Mobile Wearable and Ubiquitous Technologies · doi:10.1145/3380982 · Cited by 24
“To tackle the problem of implicit influences from different tags, we introduce the soft attention module to put weights on different tags [47].”
MethodCross-Lingual Knowledge Transferring by Structural Correspondence and Space Transfer
Wang, D., Wu, J., Yang, J., Jing, B., Zhang, W., He, X., & Zhang, H. (2021) · IEEE Transactions on Cybernetics · doi:10.1109/tcyb.2021.3051005 · Cited by 18
“Moreover, coarse-grained models only learn document-level feature representations, which often fail to capture various aspects in one real-life product review [45], [46], for example, the screen, battery, and camera of an iPhone.”
BackgroundExploiting Position Bias for Robust Aspect Sentiment Classification
Ma, F., Zhang, C., & Song, D. (2021) · Findings of the Association for Computational Linguistics: ACL (Findings of ACL) · doi:10.18653/v1/2021.findings-acl.116 · Cited by 24
Fine-grained Question-Answer sentiment classification with hierarchical graph attention network
Zeng, J., Liu, T., Jia, W., & Zhou, J. (2021) · Neurocomputing · doi:10.1016/j.neucom.2021.06.040 · Cited by 19
CBVoSD: context based vectors over sentiment domain ensemble model for review classification
Wankhade, M., Annavarapu, C. S. R., & Verma, M. K. (2021) · The Journal of Supercomputing · doi:10.1007/s11227-021-04132-5 · Cited by 18
“Wang et al. [17] used three different machine learning techniques, SVM, NB, and ME.”
MethodA Multi-Attention Network for Aspect-Level Sentiment Analysis
Zhang, Q., & Lu, R. (2019) · Future Internet · doi:10.3390/fi11070157 · Cited by 19
“[10] proposed to combine attention mechanism with LSTM to model sentences semantically, which used attention mechanism to capture the importance of different contextual information on a given aspect and solve the problem of ASA.”
BackgroundPark, S.-T., Kim, D.-Y., & Li, G. (2020) · Multimedia Tools and Applications · doi:10.1007/s11042-020-08818-5 · Cited by 18
“As a result of analysis, the ATAE-LSTM technique showed the highest accuracy of 84.0% in the classification of 3 sentiments (positivity, negativity, neutrality) and of 89.9% in the classification of 2 sentiments (positivity, negativity) [36].”
MethodInfluentialA comprehensive survey on aspect-based sentiment analysis
Gadekallu, T. R., Maddikunta, P. K. R., Kumar, N., & Kaustubh, Y. (2021) · International Journal of Engineering Systems Modelling and Simulation · doi:10.1504/ijesms.2021.119892 · Cited by 22
A span-based model for aspect terms extraction and aspect sentiment classification
Lv, Y., Wei, F., Zheng, Y., Wang, C., Wan, C., & Wang, C. (2020) · Neural Computing and Applications · doi:10.1007/s00521-020-05221-x · Cited by 22
“[30] proposed an attention-based LSTM model, which focuses on different parts of a sentence according to different aspects.”
BackgroundKasemrat, R., & Kraiwanit, T. (2025) · Intelligent Systems with Applications · doi:10.1016/j.iswa.2025.200523 · Cited by 18
Intermediate-task transfer learning for Indonesian NLP tasks
Ekakristi, A. S., Wicaksono, A. F., & Mahendra, R. (2025) · Natural Language Processing Journal · doi:10.1016/j.nlp.2025.100161 · Cited by 18
Machine learning for intraoperative prediction of viability in ischemic small intestine
Strand-Amundsen, R. J., Tronstad, C., Reims, H. M., Reinholt, F. P., Høgetveit, J. O., & Tønnessen, T. I. (2018) · Physiological Measurement · doi:10.1088/1361-6579/aae0ea · Cited by 18
“…and has demonstrated superior performance in applications such as language interpretation (Gers and Schmidhuber 2001), sentiment classification (Wang et al 2016), sound event detection (Ada-vanne et al 2016), human action recognition (Liu et al 2016) and handwriting recognition (Yousefi et al…”
BackgroundAdversarial Machine Learning on Social Network: A Survey
Guo, S., Li, X., & Mu, Z. (2021) · Frontiers in Physics · doi:10.3389/fphy.2021.766540 · Cited by 23
“[26] introduced a multi-head attention-based LSTM model to perform aspect-level sentiment analysis, they carry out their experiment on the dataset of SemEval 2014 Task 4 [27], the results of the experiment show that their model is advantageously competitive in aspect-level classification.”
MethodAspect-level sentiment classification based on location and hybrid multi attention mechanism
Wu, Y., & Li, W. (2022) · Applied Intelligence · doi:10.1007/s10489-021-02966-3 · Cited by 17
Distilroberta2gnn: a new hybrid deep learning approach for aspect-based sentiment analysis
Alhadlaq, A., & Altheneyan, A. S. (2024) · PeerJ Computer Science · doi:10.7717/peerj-cs.2267 · Cited by 23
“ATAE-LSTM computes attention scores with respect to a speci fi c aspect, enabling the model to focus on the most relevant parts of a sentence for sentiment analysis, thereby enhancing the precision of aspect-based sentiment prediction ( Wang et al., 2016 ).”
MethodEntity Linking on Chinese Microblogs via Deep Neural Network
Zeng, W., Tang, J., & Zhao, X. H. (2018) · IEEE Access · doi:10.1109/access.2018.2833153 · Cited by 17
“On the other, existing approaches neglect the word order in contexts, which has proved to be critical for natural language understanding [14].”
BackgroundMethodAspect Sentiment Model for Micro Reviews
Amplayo, R. K., & Hwang, S.-W. (2017) · Proceedings · doi:10.1109/icdm.2017.83 · Cited by 17
Graph Convolutional Networks with Structural Attention Model for Aspect Based Sentiment Analysis
Chen, J., Hou, H., Ji, Y., & Gao, J. (2019) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn.2019.8852093 · Cited by 20
“The other two sequential models, ATAE-LSTM and IAN, obtain the text representations from LSTM. IAN builds interactive attentions for target and context which outperforms other sequential models .”
BackgroundPath Travel Time Estimation using Attribute-related Hybrid Trajectories Network
Lin, X., Wang, Y., Xiao, X., Li, Z., & Bhowmick, S. S. (2019) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3357384.3357927 · Cited by 20
“To attend to the important channel of sub-path features, we design a Sub-path Attention mechanism, inspired by [1, 29].”
MethodSelf-citationAn implicit opinion analysis model based on feature-based implicit opinion patterns
Zhao, F., Zhang, Q., Tang, X., Wang, A., & Baron, C. (2020) · Artificial Intelligence Review · doi:10.1007/s10462-019-09801-9 · Cited by 17
“Wang et al. (2016) proposed an attention-based LSTM method with product feature embeddings to provide additional sentence relevance during classification.”
MethodAspect-Context Interactive Attention Representation for Aspect-Level Sentiment Classification
Wu, Z., Li, Y., Liao, J., Li, D., Li, X., & Wang, S. (2020) · IEEE Access · doi:10.1109/access.2020.2972697 · Cited by 18
“Traditional methods either use the same LSTM for aspect modeling [7], [8], or simply average its word embeddings [6].”
InfluentialDeep Learning Approaches for Sentiment Analysis on Financial Microblog Dataset
Yıldırım, S., Jothimani, D., Kavaklioğlu, C., & Bener, A. (2019) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata47090.2019.9006056 · Cited by 17
“While the superior performance of LSTM is due to its ability to predict the polarity correctly with the help of attention mechanism and aspect embedding [18].”
BackgroundElectronic word-of-mouth effects on studio performance leveraging attention-based model
Liu, Y., Fei, H., Zeng, Q., Li, B., Ma, L., Ji, D., & Ordieres-Meré, J. B. (2020) · Neural Computing and Applications · doi:10.1007/s00521-020-04937-0 · Cited by 18
“Our proposed method achieves better performance than that exhibited by the attention-based models that using attention-based convolutional neural network (A-CNN) [20], attention- based long short-term memory neural network (A-LSTM) [21], user and product attention neural network (UPA) [18] and hierarchical user attent…”
BackgroundMethodInfluentialToward Aspect-Level Sentiment Modification Without Parallel Data
Jiang, Q., Chen, L., Zhao, W. Z., & Yang, M. (2021) · IEEE Intelligent Systems · doi:10.1109/mis.2021.3052617 · Cited by 17
Benchmarking Deep Learning Methods for Aspect Level Sentiment Classification
Sharma, T., & Kaur, K. (2021) · Applied Sciences · doi:10.3390/app112210542 · Cited by 19
“[22] leveraged the idea of combining aspect embedding with LSTM.”
BackgroundMethodInfluentialWei, S., Zhu, G., Sun, Z., Li, X., & Weng, T. (2022) · Connection Science · doi:10.1080/09540091.2022.2080183 · Cited by 17
“To strengthen attention to given aspects, Wang et al. (2016) set an attention vector for each target based on LSTM to respond to specific targets.”
BackgroundEnhancing Decision Making Capacity in Tourism Domain Using Social Media Analytics
Abeysinghe, S., Manchanayake, I., Samarajeewa, C., Rathnayaka, P., Walpola, M., Nawaratne, R., Bandaragoda, T., & Alahakoon, D. (2018) · International Conference on Advances in ICT for Emerging Regions · doi:10.1109/icter.2018.8615462 · Cited by 18
KUnet: Microscopy Image Segmentation With Deep Unet Based Convolutional Networks
Chang, S., & Liao, S. W. (2019) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc.2019.8914048 · Cited by 17
“There are a lot of LSTM applications include image segmentation [18, 19], human-human interactions [20], natural language processing [21, 22].”
BackgroundNeural Feature Extraction for Contextual Emotion Detection
Mohammadi, E., Amini, H., & Kosseim, L. (2019) · International conference Recent advances in natural language processing · doi:10.26615/978-954-452-056-4_091 · Cited by 20
“Following several works that have shown significant improvement in text classification with the use of attention (e.g. Yang et al., 2016; Zhou et al., 2016; Wang et al., 2016; Cianflone et al., 2018), we incorporated an attention mechanism in our contextual emotion detection framework.”
MethodFeng, A., Gao, Z., Song, X., Ke, K., Xu, T., & Zhang, X. (2020) · Computers, materials & continua/Computers, materials & continua (Print) · doi:10.32604/cmc.2020.09913 · Cited by 16
“ATAE-LSTM Wang et al. [Wang, Huang, Zhao et al. (2016)] splices the word embedding of the target word and the word embedding of each word in the sentence as the input of LSTM network.”
BackgroundHou, Z., Du, Y., Li, W., Hu, J., Li, H., Li, X., & Chen, X. (2022) · Applied Soft Computing · doi:10.1016/j.asoc.2022.109659 · Cited by 19
Commonsense knowledge graph-based adapter for aspect-level sentiment classification
Lu, G., Yu, H., Yan, Z., & Xue, Y. (2023) · Neurocomputing · doi:10.1016/j.neucom.2023.03.002 · Cited by 18
Exploring Scope Detection for Aspect-Based Sentiment Analysis
Jiang, X., You, P., Chen, C., Wang, Z., & Zhou, G. (2023) · IEEE/ACM Transactions on Audio Speech and Language Processing · doi:10.1109/taslp.2023.3323136 · Cited by 16
“(cid:2) ATAE-LSTM [57] is a classic LSTM based model which explores the connection between an aspect and the content of a sentence with an attention-based LSTM. (cid:2) MemNet [13] is a memory based method combining a neural attention model with an external memory to calculate the importance of…”
MethodYang, B., Li, H., & Xing, Y. (2023) · International Journal of Computers Communications & Control · doi:10.15837/ijccc.2023.5.5089 · Cited by 16
Dual-channel relative position guided attention networks for aspect-based sentiment analysis
Gao, X., Fang-ai, L., Zhuang, X., Tian, X., Zhang, Y., & Liu, K. (2024) · Expert Systems with Applications · doi:10.1016/j.eswa.2024.124271 · Cited by 17
Aspect-based sentiment analysis via dual residual networks with sentiment knowledge
Zhu, C., & Ding, Q. (2024) · The Journal of Supercomputing · doi:10.1007/s11227-024-06546-3 · Cited by 17
“The introduction of the attention mechanism [6, 7] has significantly improved this aspect, allowing models to concentrate on critical information within the text and thereby enhancing the accuracy and expressive capabilities of sentiment analysis.”
Gul, S., Asif, M., Amin, F.-E., Saleem, K., & Imran, M. A. (2025) · IEEE Access · doi:10.1109/access.2025.3527367 · Cited by 16
“Later advancements introduced neural networks, which significantly improved the accuracy of ABSA tasks [16], [17], [18], [19], [20], [21], [22].”
Kim, S. K., Kim, J. B., Kim, H., Kim, L., & Kim, S. H. (2025) · Diagnostics · doi:10.3390/diagnostics15040448 · Cited by 16
“To address this limitation, we incorporated an attention mechanism into the LSTM framework [28–30], allowing the model to effectively learn complex patterns by emphasizing important temporal features.”
Dependency-Attention-Based LSTM for Target-Dependent Sentiment Analysis
Wang, X., & Chen, G. (2017) · Communications in computer and information science · doi:10.1007/978-981-10-6805-8_17 · Cited by 16
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.