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 601–700 of 1,003
An Integration Model Based on Graph Convolutional Network for Text Classification
Tang, H., Mi, Y., Xue, F., & Cao, Y. (2020) · IEEE Access · doi:10.1109/access.2020.3015770 · Cited by 33
“Wang et al. [28] introduced the attention mechanism into LSTM, which provided a new idea for text classification.”
BackgroundXiao, Y., & Zhou, G. (2020) · IEEE Access · doi:10.1109/access.2020.3019277 · Cited by 33
“Attention-Based LSTM (ATAE-LSTM) [7]: They proposed an attention-based model using the aspect embedding and word embedding to provide the solution of ALSC.”
BackgroundMethodInfluentialWang, Y., Feng, C., & Anderson, D. V. (2021) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp39728.2021.9413498 · Cited by 35
“Since then, attentionbased neural networks have been widely used in computer vision [11], natural language processing [12] and speech recognition [13].”
MethodSelf-citationAuditory Attention Detection via Cross-Modal Attention
Su, E., Cai, S., Li, P., Xie, L., & Li, H. (2021) · Frontiers in Neuroscience · doi:10.3389/fnins.2021.652058 · Cited by 38
“The attention mechanism has attracted great interest and shown promising capability in a variety of related applications such as machine translation (Luong et al., 2015), image caption generation (Xu et al., 2015) and object classification (Wang et al., 2016; Guo et al., 2019).”
BackgroundPandey, S. K., & Tripathi, A. K. (2021) · Knowledge-Based Systems · doi:10.1016/j.knosys.2021.107541 · Cited by 32
Cross-Platform Reputation Generation System Based on Aspect-Based Sentiment Analysis
Boumhidi, A., Benlahbib, A., & Nfaoui, E. H. (2021) · IEEE Access · doi:10.1109/access.2021.3139956 · Cited by 32
“In [19], the authors proposed an attention-based long short-term memory (LSTM) [20] for aspect-level sentiment classification.”
BackgroundXu, M., Zeng, B., Yang, H., Chi, J., Chen, J., & Liu, H. (2022) · Neurocomputing · doi:10.1016/j.neucom.2021.12.084 · Cited by 32
Aspect Based Sentiment Analysis of Product Review Using Memory Network
Ismet, H. T., Mustaqim, T., & Purwitasari, D. (2022) · Scientific Journal of Informatics · doi:10.15294/sji.v9i1.34094 · Cited by 31
“The use of GRU as a method of learning aspect context information is carried out by Wang [7] to get a”
MethodInfluentialForghanparast, F., & Mohammadi, G. (2022) · Water · doi:10.3390/w14192972 · Cited by 34
“Attention is a deep learning strategy and can be viewed as essentially implementing a neural network within another neural network to weigh various portions of a sequence for relative feature importance [103,104].”
BackgroundDeep learning applications on cybersecurity: A practical approach
Miranda-García, A., Rego, A. Z., Pastor-López, I., Sanz, B., Tellaeche, A., de la Puerta, J. G., & Bringas, P. G. (2023) · Neurocomputing · doi:10.1016/j.neucom.2023.126904 · Cited by 40
Aspect category sentiment analysis based on prompt-based learning with attention mechanism
Ping, Z., Sang, G., Liu, Z., & Zhang, Y. (2023) · Neurocomputing · doi:10.1016/j.neucom.2023.126994 · Cited by 34
Multimodal Autoencoder Predicts fNIRS Resting State From EEG Signals
Sirpal, P., Damseh, R., Peng, K., Nguyen, D. K., & Lesage, F. (2021) · Neuroinformatics · doi:10.1007/s12021-021-09538-3 · Cited by 33
“The encoder LSTM receives input sequences and encodes them into a feature vector as the LSTM generates hidden outputs (Lipton et al., 2016; Wang et al., 2016).”
MethodTextFlint: Unified Multilingual Robustness Evaluation Toolkit for Natural Language ProcessingPreprint
Gui, T., Wang, X., Zhang, Q., Liu, Q., Zou, Y., Zhou, X., Zheng, R., Zhang, C., Wu, Q., Ye, J., et al. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2103.11441 · Cited by 43
Aspect-Based Sentiment Analysis with Explicit Sentiment Augmentations
Ouyang, J., Yang, Z., Liang, S., Wang, B., Wang, Y., & Li, X. (2024) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v38i17.29849 · Cited by 30
Self-citationUnveiling the frontiers of deep learning: Innovations shaping diverse domains
Ahmed, S. F., Alam, M. S. B., Kabir, M., Afrin, S., Rafa, S. J., Mehjabin, A., & Gandomi, A. H. (2025) · Applied Intelligence · doi:10.1007/s10489-025-06259-x · Cited by 39
“Attention-based LSTM Question answering Better performance than baseline approaches Modeling more than one aspect simultaneously with the attention mechanism would be an interesting addition to the experiment [143]”
A Comparative Evaluation of Transformer-Based Language Models for Topic-Based Sentiment Analysis
Tzimiris, S., Nikiforos, S., Nikiforos, M. N., Mouratidis, D., & Kermanidis, K. L. (2025) · Electronics · doi:10.3390/electronics14152957 · Cited by 35
The optimally designed dynamic memory networks for targeted sentiment classification
Zhang, Z., Wang, L., Zou, Y., & Gan, C. (2018) · Neurocomputing · doi:10.1016/j.neucom.2018.04.068 · Cited by 33
An LSTM-CNN attention approach for aspect-level sentiment classification
Jiang, M., Zhang, W., Zhang, M., Wu, J., & Wen, T. (2019) · Journal of Computational Methods in Sciences and Engineering · doi:10.3233/jcm-190022 · Cited by 30
“This shows LSTM can capture semantic relations be-tween aspect and context words in a more scalable way than feature based SVM [16], without careful engineering of features.”
Sindhu, C., & Vadivu, G. (2020) · Microprocessors and Microsystems · doi:10.1016/j.micpro.2020.103365 · Cited by 32
Optimizing Attention for Sequence Modeling via Reinforcement Learning
Fei, H., Zhang, Y., Ren, Y., & Ji, D. (2021) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2021.3053633 · Cited by 33
Shim, H., Lowet, D., Luca, S., & Vanrumste, B. (2021) · IEEE Access · doi:10.1109/access.2021.3101867 · Cited by 33
“There has been significant improvement in ABSA systems over the past few years thanks to the recent progress of deep neural network (DNN) based NLP models, [10], [12], [13], [15], [17].”
BackgroundDual-channel and multi-granularity gated graph attention network for aspect-based sentiment analysis
Wang, Y., Yang, N., Miao, D., & Chen, Q. (2022) · Applied Intelligence · doi:10.1007/s10489-022-04198-5 · Cited by 31
“[12] first used the attention mechanism on LSTM to capture important emotional information related to the aspect and appends the target embedding with each word embedding.”
MethodSelf-citationHu, Z., Wang, Z., Wang, Y., & Tan, A. (2023) · Expert Systems with Applications · doi:10.1016/j.eswa.2022.119492 · Cited by 31
Self-citationLiu, H., Li, X., Lu, W., Cheng, K., & Liu, X. (2024) · Expert Systems with Applications · doi:10.1016/j.eswa.2024.123981 · Cited by 34
Li, K., Xian, X., Wang, J., & Yu, N. (2018) · Applied Surface Science · doi:10.1016/j.apsusc.2018.11.214 · Cited by 32
“As a simple and effective method that can be used to encode sequence data with its importance, it has shown significant improvement in various tasks in natural language processing, including text summarization [73], sentiment classification [95], semantic parsing [9], etc.”
MethodDai, Z., Peng, C., Chen, H., & Ding, Y. (2020) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2020.emnlp-main.565 · Cited by 34
Wood broken defect detection with laser profilometer based on Bi-LSTM network
Xu, Z., Lin, Y., Chen, D., Yuan, M., Zhu, Y., Ai, Z., & Yuan, Y. (2023) · Expert Systems with Applications · doi:10.1016/j.eswa.2023.122789 · Cited by 29
Wang, X., Liu, L., Chen, Z., Wang, H., & Yu, B. (2025) · Expert Systems with Applications · doi:10.1016/j.eswa.2025.127172 · Cited by 29
Multiple perspective attention based on double BiLSTM for aspect and sentiment pair extract
Fu, Y., Liao, J., Li, Y., Wang, S., Li, D., & Li, X. (2021) · Neurocomputing · doi:10.1016/j.neucom.2021.01.079 · Cited by 31
“A typical ATAE model based on an LSTM network with an attention mechanism used category embedding to focus on category-specific sentiment information in sentences [31].”
MethodInfluentialExploiting BERT to Improve Aspect-Based Sentiment Analysis Performance on Persian Language
Jafarian, H., Taghavi, A. H., Javaheri, A., & Rawassizadeh, R. (2021) · International Conference on Web Research (ICWR) · doi:10.1109/icwr51868.2021.9443131 · Cited by 36
“• Reference [11] using attention-based long shortterm memory network (ATAE-LSTM)”
BackgroundMethodFeng, S., & Feng, Y. (2021) · IEEE Access · doi:10.1109/access.2021.3136712 · Cited by 29
“Attention based LSTM, was used to generate translation dictionary with relative probability distribution [15].”
BackgroundMethodResearch on Sentiment Analysis Model of Short Text Based on Deep Learning
Zhou, Z. G. (2022) · Scientific Programming · doi:10.1155/2022/2681533 · Cited by 29
“Wang added a self-attention mechanism (Attention Mechanism) after the output storey of the LSTM network [15] and obtained the context information of the LSTM output unit attention means for relevant automatic acquisition.”
BackgroundZhou, X., Zhang, T., Cheng, C., & Song, S. (2022) · Applied Intelligence · doi:10.1007/s10489-022-03851-3 · Cited by 34
“Wang et al. [21] added aspect categories to each LSTM time step input and used the attention mechanism to capture the context related to aspect words.”
MethodResultLiu, B., Lin, T., & Li, M. (2023) · Knowledge-Based Systems · doi:10.1016/j.knosys.2023.110339 · Cited by 30
MAPA BiLSTM-BERT: multi-aspects position aware attention for aspect level sentiment analysis
Wankhade, M., Annavarapu, C. S. R., & Abraham, A. (2023) · The Journal of Supercomputing · doi:10.1007/s11227-023-05112-7 · Cited by 31
“[15] suggested a sentiment-aligned topic method to predict product aspect ratings.”
BackgroundMethodJiang, X., Ren, B., Wu, Q., Wang, W., & Li, H. (2024) · Complex & Intelligent Systems · doi:10.1007/s40747-024-01570-5 · Cited by 35
“Wang et al. [17] incorporated Long Short-Term Memory (LSTM) models into tasks of aspect-based sentiment analysis, unveiling the Target-Dependent Long Short-Term Memory (TD-LSTM) and Target-Connection Long Short-Term Memory (TC-LSTM) models, both predicated on LSTM architecture.”
A Convolutional Neural Network for Aspect-Level Sentiment Classification
Xing, Y., Xiao, C., Wu, Y., & Ding, Z. (2019) · International Journal of Pattern Recognition and Artificial Intelligence · doi:10.1142/s0218001419590468 · Cited by 28
Nguyen, H.-T., & Nguyen, L.-M. (2019) · Expert Systems with Applications · doi:10.1016/j.eswa.2019.113065 · Cited by 29
Training Deep Neural Networks Using Posit Number System
Lu, J., Lu, S., Wang, Z., Fang, C., Lin, J. T., Wang, Z., & Du, L. (2019) · IEEE International System-on-Chip Conference (SOCC) · doi:10.1109/socc46988.2019.1570558530 · Cited by 32
“Recently deep neural networks (DNNs) have made a great success in many real-world applications, such as image clas-sification [1], speech recognition [2], and natural language processing [3].”
BackgroundFusing Knowledge and Aspect Sentiment for Explainable Recommendation
Bai, P., Yang, X., & Yong-sheng, X. (2020) · IEEE Access · doi:10.1109/access.2020.3012347 · Cited by 28
“[30] proposed an attention-based LSTM for aspect sentiment classification, which mainly uses the attention mechanism to capture the importance of different context information for a given aspect.”
BackgroundNopember, I. T. S., Setiawan, E. I., Ferry, F., Surabaya, I. S. D. T. T., Santoso, J., Nopember, I. T. S., Sumpeno, S., Nopember, I. T. S., Fujisawa, K., Purnomo, M. H., et al. (2020) · International journal of intelligent engineering and systems · doi:10.22266/ijies2020.1031.35 · Cited by 32
“Attention has been proven to improve the performance of several sentiment analysis approaches by focusing on the aspect [16].”
BackgroundMethodAggarwal, A., Wadhawan, A., Chaudhary, A., & Maurya, K. (2020) · Workshop on Noisy User-generated Text (W-NUT) · doi:10.18653/v1/2020.wnut-1.2 · Cited by 28
DUET: Boosting Deep Neural Network Efficiency on Dual-Module Architecture
Liu, L., Qu, Z., Deng, L., Tu, F., Li, S., Hu, X., Gu, Z., Ding, Y., & Xie, Y. (2020) · IEEE/ACM International Symposium on Microarchitecture (MICRO) · doi:10.1109/micro50266.2020.00066 · Cited by 31
“Deep Neural Networks (DNNs) have led to important breakthroughs that expand the possibilities of applying artificial intelligence (AI) to many domains, including visual and auditory recognition [1], [21], [25], [44], natural language processing [14], [46], autonomous driving [9], medical analysis [16], and so forth.”
BackgroundFilter gate network based on multi-head attention for aspect-level sentiment classification
Zhou, Z., & Liu, F. (2021) · Neurocomputing · doi:10.1016/j.neucom.2021.02.041 · Cited by 29
Research on state prediction method of tobacco curing process based on model fusion
Wang, Y., & Qin, L. (2021) · Journal of Ambient Intelligence and Humanized Computing · doi:10.1007/s12652-021-03129-5 · Cited by 30
“LSTM neural network (Shi et al. 2015; Gers et al. 2002; Wang et al. 2016) and XGBoost (Chen and Guestrin 2016; Yu et al. 2020) are chosen to establish a tobacco leaf curing state prediction fusion model SPFM and enable a high-precision prediction.”
MethodSelf-citationYang, Z., Gao, Y., & Fu, X. (2021) · Annals of Operations Research · doi:10.1007/s10479-021-04339-y · Cited by 28
“Long term short memory network (LSTM) (Gao et al., 2020a, 2020b, 2020c; Hammad et al., 2021;Wang et al., 2016), as a variant of recurrent neural network (RNN), was proposed by Hochreiter and Schmidhuber to overcome gradient vanishing problem.”
BackgroundRetractedMulti-view informed attention-based model for Irony and Satire detection in Spanish variants
Bueno, R. O., Rosso, P., & Pagóla, J. E. M. (2021) · Knowledge-Based Systems · doi:10.1016/j.knosys.2021.107597 · Cited by 30
Knowledge-based Temporal Fusion Network for Interpretable Online Video Popularity Prediction
Tang, S., Li, Q., Ma, X., Gao, C., Wang, D., Jiang, Y., Ma, Q., Zhang, A., & Chen, H. (2022) · International World Wide Web Conference (WWW) · doi:10.1145/3485447.3511934 · Cited by 32
“There are two primary motivations for us to choose the Attentionbased LSTM [29] modeling the temporal evolution process of popularity.”
BackgroundMethodInfluentialEffective inter-aspect words modeling for aspect-based sentiment analysis
Gu, T., Zhao, H., & Li, M. (2022) · Applied Intelligence · doi:10.1007/s10489-022-03630-0 · Cited by 31
“Because LSTM cannot recognize the words that most effectively represent aspect phrases [46], we decide to add the self-attention mechanism to capture the information on the potential relationship between different aspect words and the same category of aspect words.”
BackgroundSurvey on Aspect Category Detection
Chebolu, S. U. S., Rosso, P., Kar, S., & Solorio, T. (2022) · ACM Computing Surveys · doi:10.1145/3544557 · Cited by 34
Multi-Task Learning Model Based on BERT and Knowledge Graph for Aspect-Based Sentiment Analysis
He, Z., Wang, H., & Zhang, X.-P. S. (2023) · Electronics · doi:10.3390/electronics12030737 · Cited by 31
Sun, B., Song, X., Li, W., Liu, L., Gong, G., & Zhao, Y. K. (2023) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2023.107224 · Cited by 31
Zarandi, A. K., & Mirzaei, S. (2023) · Multimedia Tools and Applications · doi:10.1007/s11042-023-17701-y · Cited by 30
Syntactic and Semantic Aware Graph Convolutional Network for Aspect-Based Sentiment Analysis
Chen, J., Fan, H., & Wang, W. (2024) · IEEE Access · doi:10.1109/access.2024.3364353 · Cited by 28
“Sequential models combined with attention mechanisms have been employed to address the relationship between context and aspect words [23], [24], [25], [26].”
MethodA sentiment information Collector–Extractor architecture based neural network for sentiment analysis
Shuang, K., Zhang, Z., Guo, H., & Loo, J. (2018) · Information Sciences · doi:10.1016/j.ins.2018.08.026 · Cited by 28
“LSTM is developed [12] and achieved more superior performance then both tradition RNN structure and GRU [23].”
MethodA Deep Neural Network Model for Target-based Sentiment Analysis
Chen, S., Peng, C., Cai, L., & Guo, L. (2018) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn.2018.8489180 · Cited by 31
“However, these methods haven’t paid much attention to the fact that different context words might have different contributions to targets’ sentiment polarities [8].”
BackgroundInfluentialLin, P., Yang, M., & Lai, J. (2021) · IEEE/ACM Transactions on Audio Speech and Language Processing · doi:10.1109/taslp.2021.3058540 · Cited by 34
“Attention mechanism can focus on important parts of a specific aspect and its contexts [2], [7], [8], while memory network can store context information and apply multi-hop attention [1], [9].”
BackgroundTransferable End-to-End Aspect-based Sentiment Analysis with Selective Adversarial LearningPreprint
Li, Z., Li, X., Wei, Y., Bing, L., Zhang, Y., & Yang, Q. (2019) · arXiv (Cornell University) · doi:10.48550/arxiv.1910.14192 · Cited by 28
Semi-supervised target-oriented sentiment classification
Xu, W., & Tan, Y. (2019) · Neurocomputing · doi:10.1016/j.neucom.2019.01.059 · Cited by 30
Aspect-Based Sentiment Classification with Attentive Neural Turing Machines
Mao, Q., Li, J., Wang, S., Zhang, Y., Peng, H. M., He, M., & Wang, L. (2019) · International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2019/714 · Cited by 37
Relationship Identification Between Conversational Agents Using Emotion Analysis
Qamar, S., Mujtaba, H., Majeed, H., & Beg, M. O. (2021) · Cognitive Computation · doi:10.1007/s12559-020-09806-5 · Cited by 27
“Recently, deep learning has been particularly successful in extracting sentiments from text [27, 28].”
BackgroundFine-grained attention-based phrase-aware network for aspect-level sentiment analysis
Liao, W., Zhou, J., Wang, Y., Yin, Y., & Zhang, X. (2021) · Artificial Intelligence Review · doi:10.1007/s10462-021-10080-6 · Cited by 28
“− (Wang et al. 2016)(attention-based LSTM with aspect embedding) is an extension of AE-LSTM that uses an attention mechanism.”
BackgroundMethodInfluentialSelf-citationNazir, A., Rao, Y., Wu, L., & Sun, L. (2022) · IEEE Transactions on Affective Computing · doi:10.1109/taffc.2022.3208216 · Cited by 30
“But lately, with the advancements in deep learning mechanisms, much work on ABSA is focused on deep neural networks, such as recursive neural networks [14], [15], [16], to improve feature representations.”
BackgroundMethodInfluentialRoman Urdu Sentiment Analysis Using Transfer Learning
Li, D., Ahmed, K., Zheng, Z., Mohsan, S. A. H., Alsharif, M. H., Hadjouni, M., Jamjoom, M. M., & Mostafa, S. M. (2022) · Applied Sciences · doi:10.3390/app122010344 · Cited by 34
“[44] presented an attention-based LSTM Model that could concentrate on different sentence segments.”
BackgroundResearch on non-dependent aspect-level sentiment analysis
Jiang, L., Li, Y., Liao, J., Zou, Z., & Jiang, C. (2023) · Knowledge-Based Systems · doi:10.1016/j.knosys.2023.110419 · Cited by 29
Retrieval Contrastive Learning for Aspect-Level Sentiment Classification
Jian, Z., Li, J., Wu, Q., & Yao, J. (2023) · Information Processing & Management · doi:10.1016/j.ipm.2023.103539 · Cited by 30
Federated Freeze BERT for text classification
Galal, O., Abdel-Gawad, A. H., & Farouk, M. (2024) · Journal Of Big Data · doi:10.1186/s40537-024-00885-x · Cited by 32
Joint Inference for Aspect-level Sentiment Analysis by Deep Neural Networks and Linguistic Hints
Wang, Y., Chen, Q., Ahmed, M., Li, Z., Pan, W., & Liu, H. (2019) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2019.2947587 · Cited by 28
“aspect embeddings are used to determine the attention weight; ATAE-LSTM [47].”
BackgroundMethodInfluentialSelf-citationQMLSC: A quantum multimodal learning model for sentiment classification
Li, Y., Qu, Y., Zhou, R.-G., & Zhang, J. (2025) · Information Fusion · doi:10.1016/j.inffus.2025.103049 · Cited by 39
Li, J., Yang, H., & Zong, C. (2018) · International Conference on Computational Linguistics · Cited by 39
Wang, J., Sun, C., Li, S., Wang, J., Si, L., Zhang, M., Liu, X., & Zhou, G. (2019) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/d19-1560 · Cited by 26
“Besides, neural networks have been widely adopted for performing a closely related task, i.e., Sentence-level As-pect Sentiment Classification (Wang et al., 2016; Tang et al., 2016; Wang and Lu, 2018).”
MethodInfluentialExamining differences among book reviews from various online platforms
Zhang, C., Tong, T., & Bu, Y. (2019) · Online Information Review · doi:10.1108/oir-01-2019-0037 · Cited by 27
Gao, Y., Liu, J., Li, P., & Zhou, D. M. (2019) · IEEE Access · doi:10.1109/access.2019.2954590 · Cited by 26
“We use the SemEval competition dataset to evaluate the CEHEAT network at the sentence level of aspect-level sentiment classification [3].”
BackgroundMethodInfluentialTowards Automatic Detection and Explanation of Hate Speech and Offensive Language
Dorris, W., Hu, R., Vishwamitra, N., Luo, F., & Costello, M. (2020) · doi:10.1145/3375708.3380312 · Cited by 26
“LSTMs specifically have been successfully applied to various sequence-based tasks such as sentiment analysis [18], machine translation [1] and caption generation [20].”
MethodDetecting the target of sarcasm is hard: Really??
Parameswaran, P., Trotman, A., Liesaputra, V., & Eyers, D. M. (2021) · Information Processing & Management · doi:10.1016/j.ipm.2021.102599 · Cited by 32
Harshness-aware sentiment mining framework for product review
Wang, X., Zhou, T., Wang, X., & Fang, Y. (2021) · Expert Systems with Applications · doi:10.1016/j.eswa.2021.115887 · Cited by 29
Zhao, L., Zhu, Y., & Zhao, T. (2022) · Mathematics · doi:10.3390/math10162921 · Cited by 30
Self-citationAspect Sentiment Triplet Extraction: A Seq2Seq Approach With Span Copy Enhanced Dual Decoder
Zhang, Z., Zuo, Y., & Wu, J. (2022) · IEEE/ACM Transactions on Audio Speech and Language Processing · doi:10.1109/taslp.2022.3198802 · Cited by 27
“Many of them aim at solving a single sub-task [5], [6], [8], [11], [31], [32], [33], [34], [35], [36], [37], [38], [39], [40], which constrains their practical use.”
BackgroundPandey, A., & Vishwakarma, D. K. (2023) · Knowledge-Based Systems · doi:10.1016/j.knosys.2023.110515 · Cited by 27
Ahmed, J., & Green, R. (2023) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2023.107339 · Cited by 28
PCA: Progressive class-wise attention for skin lesions diagnosis
Naveed, A., Naqvi, S. S., Khan, T. M., & Razzak, I. (2023) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2023.107417 · Cited by 26
Sentiment analysis from textual data using multiple channels deep learning models
Rajesh, A., & Hiwarkar, T. (2023) · Journal of Electrical Systems and Information Technology · doi:10.1186/s43067-023-00125-x · Cited by 32
“Other than this, Wang et al. [13] also proposed an attention-based LSTM network that focuses on various parts of the sentences.”
BackgroundAhmad, K. M., Liu, Q., Khalil, M. M. Y., Gan, Y., Khan, A. A., Liu, X., & Lang, J. (2024) · Knowledge-Based Systems · doi:10.1016/j.knosys.2024.112169 · Cited by 29
How to Make Attention Mechanisms More Practical in Malware Classification
Ma, X., Guo, S., Li, H., Pan, Z., Qiu, J., Ding, Y., & Chen, F. (2019) · IEEE Access · doi:10.1109/access.2019.2948358 · Cited by 26
A comprehensive review on feature set used for anaphora resolution
Lata, K., Singh, P., & Dutta, K. (2020) · Artificial Intelligence Review · doi:10.1007/s10462-020-09917-3 · Cited by 35
Zhang, P., Fu, M., Zhao, R., Zhang, H., & Luo, C. (2024) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2024.3485108 · Cited by 26
“Text aspect-based sentiment analysis models include: AE-LSTM [53] is an efficient extended form of LSTM that utilizes an attention mechanism to capture important contextual information related to aspects; TD-LSTM [9] is another variant of LSTM, which uses two bidirectional LSTMs to model the left…”
Ridoy, S. Z., Shaon, M. S. H., Cuzzocrea, A., & Akter, M. S. (2024) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata62323.2024.10825609 · Cited by 35
“Our experimental results demonstrate that the ensemble stacking approach, which combines the strengths of multiple transformer-based models, outperforms individual models in detecting vulnerabilities in source code.”
A relative position attention network for aspect-based sentiment analysis
Wu, C., Xiong, Q., Gao, M., Li, Q., Yu, Y., & Wang, K. (2020) · Knowledge and Information Systems · doi:10.1007/s10115-020-01512-w · Cited by 26
“Yi et al. [35] proposed AT-LSTM, which used modeling word-aspect relationships method to incorporate aspect information into the LSTM model.”
MethodInfluentialA Novel End-to-End Corporate Credit Rating Model Based on Self-Attention Mechanism
Chen, B., & Long, S. (2020) · IEEE Access · doi:10.1109/access.2020.3036469 · Cited by 28
“Long short-term memory units are brought out based on RNN to solve this problem [59], [60].”
BackgroundVariable-Depth Convolutional Neural Network for Text Classification
Chan, K., Im, S., & Ke, W. (2020) · Communications in computer and information science · doi:10.1007/978-3-030-63823-8_78 · Cited by 25
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. (2023) · Smart Health · doi:10.1016/j.smhl.2023.100373 · Cited by 26
Syntactic and semantic analysis network for aspect-level sentiment classification
Zhang, D., Zhu, Z., Kang, S., Zhang, G., & Liu, P. (2021) · Applied Intelligence · doi:10.1007/s10489-021-02189-6 · Cited by 26
“Wang et al. [18]. proposed Attention-based Long Short-Term Memory with Aspect Embedding (ATAE-LSTM), which combines attention with LSTM, and uses attention to obtain more important context information for different aspect terms.”
MethodXu, G., Liu, P., Zhu, Z., Liu, J., & Xu, F. (2021) · Applied Sciences · doi:10.3390/app11083640 · Cited by 30
“[5] proposed using attention-based to identify important sentiment information related to aspects.”
BackgroundLi, Y., Chen, C., Chen, F., Chen, C., Gao, R., Yang, B., Si, R., & Lv, X. (2021) · Photodiagnosis and Photodynamic Therapy · doi:10.1016/j.pdpdt.2021.102382 · Cited by 27
Zhang, B., Geng, Z., Zhang, H., & Pan, J. (2021) · Journal of Cleaner Production · doi:10.1016/j.jclepro.2021.130101 · Cited by 25
Yang, Q., Kadeer, Z., Gu, W., Sun, W., & Wumaier, A. (2022) · IEEE Access · doi:10.1109/access.2022.3228299 · Cited by 26
“ATAE-LSTM [3] utilizes LSTM and attention mechanism to interact information by splicing aspect words and context, and explore the connection between aspect and context.”
BackgroundMethodInfluentialFederated Split BERT for Heterogeneous Text Classification
Lit, Z., Sit, S., Wang, J., & Xiao, J. Z. (2022) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn55064.2022.9892845 · Cited by 35
“Pre-trained models such as ELMo [1], GPT [2] and BERT [3] have achieved great success in many NLP tasks, such as sentiment classification [4], natural language inference [5], and question answering [6].”
MethodZhang, B., Fu, X., Luo, C., Ye, Y., Li, X., & Jing, L. (2023) · IEEE Transactions on Affective Computing · doi:10.1109/taffc.2023.3239540 · Cited by 25
“For comparison, we adopt several strong sentiment classifi-cation methods as baselines: (cid:2) AT-LSTM [55]: This method first utilizes the standard LSTM model to encode the sentiment representation and then uses the attention mechanism to model the aspect-related information.”
MethodDynamic impacts of online investor sentiment on international crude oil prices
Zhao, L., Xing, Y.-Y., Zhao, Q.-R., & Chen, X.-H. (2023) · Resources Policy · doi:10.1016/j.resourpol.2023.103506 · Cited by 25
Self-citation
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.