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 701–800 of 1,003
Aspect-based sentiment analysis of drug reviews using multi-task learning based dual BiLSTM model
Rani, S., & Jain, A. (2023) · Multimedia Tools and Applications · doi:10.1007/s11042-023-16360-3 · Cited by 30
“( ) The input gate is denoted as i t , representing the information that is considered for inclusion Building upon the work of Wang et al. [35], we propose a new dual BiLSTM model constructed with two independent BiLSTM layers, which are designed to capture more contextual information and enhance…”
Chu, Z., Wang, X., Jin, M., Zhang, N., Gao, Q., & Shao, L.-H. (2024) · Axioms · doi:10.3390/axioms13030207 · Cited by 31
Sentiment Classification towards Question-Answering with Hierarchical Matching Network
Shen, C., Sun, C., Wang, J., Kang, Y., Li, S., Liu, X., Si, L., Zhang, M., & Zhou, G. (2018) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/d18-1401 · Cited by 25
“…sentiment classification, which models n -gram interactions based on tensor product and evaluates all non-Beauty consecutive n -gram vectors as a feature mapping operator for CNNs. • Attention-LSTM (Wang et al., 2016) : This is a state-of-the-art approach to aspect-level sentiment classification.”
BackgroundZhou, Z., Fang-ai, L., & Wang, Q. (2019) · IEEE Access · doi:10.1109/access.2019.2938854 · Cited by 26
“It gets the hidden vector of each word in the sentence and takes the last hidden vector as the final representation of the sentence and then inputs the SoftMax layer [28].”
BackgroundMethodInfluentialUnderstanding and Predicting Users’ Rating Behavior: A Cognitive Perspective
Li, Q., Zeng, D. D., Xu, D. J., Liu, R., & Yao, R. (2020) · INFORMS journal on computing · doi:10.1287/ijoc.2019.0919 · Cited by 35
Khan, J., & Lee, Y.-K. (2019) · Applied Sciences · doi:10.3390/app9245562 · Cited by 28
“Recently, deep learning-based aspect extraction [52], attention-based LSTM [53] and capsule networks [54,55] have also been widely used for sentiment analysis and challenging NLP applications that yield state-of-the-art prediction results.”
BackgroundTarget Embedding and Position Attention with LSTM for Aspect Based Sentiment Analysis
Xu, B., Wang, X., Yang, B., & Kang, Z. (2020) · International Conference on Mathematics and Artificial Intelligence (ICMAI) · doi:10.1145/3395260.3395280 · Cited by 27
“The experiment results of CNN and ATAE-LSTM are retrieved from the experiment results released by [2].”
MethodJoint Aspect-Sentiment Analysis with Minimal User Guidance
Zhuang, H., Guo, F., Zhang, C., Liu, L., & Han, J. (2020) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3397271.3401179 · Cited by 25
“Most existing studies on aspect-based sentiment analysis adopt a supervised framework [7, 10, 15, 18, 22, 36, 40, 41, 45], where a significant number of labeled sentences are required to train the model.”
BackgroundAspect-Level Sentiment Analysis Based on Syntax-Aware and Graph Convolutional Networks
Gu, Q., Wang, Z., Zhang, H., Sui, S. Y., & Wang, R. (2024) · Applied Sciences · doi:10.3390/app14020729 · Cited by 24
Target-Guided Structured Attention Network for Target-Dependent Sentiment Analysis
Zhang, J., Chen, C., Liu, P., He, C., & Leung, C. W.-K. (2020) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00308 · Cited by 27
Detecting Dependency-Related Sentiment Features for Aspect-Level Sentiment Classification
Zhang, X., Xu, J., Cai, Y., Tan, X., & Zhu, C. (2021) · IEEE Transactions on Affective Computing · doi:10.1109/taffc.2021.3063259 · Cited by 25
“ATAE-LSTM [10], AB-LSTM [42] and AF-LSTM [43] use LSTM to generate sentiment information and attention mechanism to select tar-get-related sentiment features.”
BackgroundMethodInfluentialForecasting Nonlinear Systems with LSTM: Analysis and Comparison with EKF
Caña, J. P. L., Herrero, J., & López, J. M. (2021) · Italian National Conference on Sensors · doi:10.3390/s21051805 · Cited by 21
Fine-Grained Sentiment Analysis of Political Tweets with Entity-Aware Multimodal Network
Yang, L., Yu, J., Zhang, C., & Na, J. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-71292-1_31 · Cited by 29
Predicting user visual attention in virtual reality with a deep learning model
Li, X., Shan, Y., Chen, W., Wu, Y., Hansen, P., & Perrault, S. T. (2021) · Virtual Reality · doi:10.1007/s10055-021-00512-7 · Cited by 27
SALNet: Semi-supervised Few-Shot Text Classification with Attention-based Lexicon Construction
Lee, J.-H., Ko, S., & Han, Y.-S. (2021) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v35i14.17558 · Cited by 30
“We use an attention-based LSTM (Wang et al. 2016) for constructing a set of crucial words for text classification.”
MethodMulti-task BERT for Aspect-based Sentiment Analysis
Wang, Y., Chen, Q., & Wang, W. (2021) · IEEE International Conference on Smart Computing · doi:10.1109/smartcomp52413.2021.00077 · Cited by 28
Self-citationLiang, B., Su, H., Yin, R., Gui, L., Yang, M., Zhao, Q., Yu, X., & Xu, R. (2021) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2021.emnlp-main.19 · Cited by 29
“Many existing research efforts focus on ACSA with deep learning methods to attend the significant information for the aspect category in sentiment prediction (Wang et al., 2016; Cheng et al., 2017; Liang et al., 2019a,b; Li et al., 2020a; Chen et al., 2020; Li et al., 2020b; Liang et al., 2020a).”
BackgroundMethodInfluentialInland harmful algal blooms (HABs) modeling using internet of things (IoT) system and deep learning
Kwon, D. H., Hong, S. M., Abbas, A., Pyo, J., Lee, H., Baek, S., & Cho, K. H. (2022) · Environmental Engineering Research · doi:10.4491/eer.2021.280 · Cited by 27
“the attention mechanism is the 48 overcoming approach with explainability by analyzing the features of attention weight [33].”
BackgroundAspect-Level Sentiment Analysis via a Syntax-Based Neural Network
Zhang, R., Chen, Q., Zheng, Y., Mensah, S., & Mao, Y. (2022) · IEEE/ACM Transactions on Audio Speech and Language Processing · doi:10.1109/taslp.2022.3190731 · Cited by 25
“Several works including [4], [5], [9], [23]–[27] have successfully developed semantic-based methods for ALSC.”
BackgroundMethodInfluentialDai, D., Chen, T., Xia, S., Wang, G., & Chen, Z. (2022) · Knowledge-Based Systems · doi:10.1016/j.knosys.2022.109506 · Cited by 24
Bie, Y., Yang, Y. Z., & Zhang, Y. (2022) · Tsinghua Science & Technology · doi:10.26599/tst.2021.9010095 · Cited by 25
Multiple graph convolutional networks for aspect-based sentiment analysis
Ma, Y., Song, R., Gu, X., Shen, Q., & Xu, H. (2022) · Applied Intelligence · doi:10.1007/s10489-022-04023-z · Cited by 24
“[8] introduced the attention mechanism and set an attention vector for each aspect based on long shortterm memory (LSTM) network, which is an effective way to strengthen the neural model to focus on the relevant parts of a sentence.”
BackgroundMethodAbdalla, H. I., & Amer, A. A. (2022) · Information Sciences · doi:10.1016/j.ins.2022.10.004 · Cited by 26
Li, Z. (2022) · International Journal of Environmental Research and Public Health · doi:10.3390/ijerph192013555 · Cited by 24
“In this study, we introduced the attention mechanism after the last layer of LSTM model [36,37].”
MethodKnowledge-Enhanced Dual-Channel GCN for Aspect-Based Sentiment Analysis
Zhang, Z., Ma, Z., Cai, S., Chen, J., & Xue, Y. (2022) · Mathematics · doi:10.3390/math10224273 · Cited by 27
“• R-GAT [4]: It reshapes and prunes an ordinary dependency parse tree to obtain an aspect-oriented dependency tree structure rooted at a target aspect.”
BackgroundMethodInfluentialAttention-based BILSTM for the degradation trend prediction of lithium battery
Guo, J., Liu, M., Luo, P., Chen, X., Yu, H., & Wei, X. (2023) · Energy Reports · doi:10.1016/j.egyr.2023.03.056 · Cited by 24
Xin, X., Wumaier, A., Kadeer, Z., & He, J. (2023) · Applied Sciences · doi:10.3390/app13085085 · Cited by 24
“[7] captured the importance of different contextual information to a given aspect word through the attention mechanism, and the attention mechanism and LSTM are combined to model the semantics of sentences and solve the problem of aspect-level sentiment analysis.”
BackgroundDual-Channel Span for Aspect Sentiment Triplet Extraction
Li, P., Li, P., & Zhang, K. (2023) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/2023.emnlp-main.17 · Cited by 43
Graph Convolutional Network with Syntactic Dependency for Aspect-Based Sentiment Analysis
Zhang, F., Zheng, W., & Yang, Y. (2024) · International Journal of Computational Intelligence Systems · doi:10.1007/s44196-024-00419-6 · Cited by 31
“Wang et al. [29] presented an LSTM incorporating a variant of the attention mechanism, that connected aspect vectors to sentence hidden representations to calculate attention weights.”
MTL-AraBERT: An Enhanced Multi-Task Learning Model for Arabic Aspect-Based Sentiment Analysis
Fadel, A. S., Saleh, M., Salama, R. M., & Abulnaja, O. A. (2024) · Computers · doi:10.3390/computers13040098 · Cited by 28
X-News dataset for online news categorization
Yousafzai, S. N., Shahbaz, H., Ali, A., Qamar, A., Nasir, I. M., Tehsin, S., & Damaševičius, R. (2024) · International Journal of Intelligent Computing and Cybernetics · doi:10.1108/ijicc-04-2024-0184 · Cited by 24
Attention-Based Memory Network for Text Sentiment Classification
Hu, H., Liu, J., & Liu, G. (2018) · IEEE Access · doi:10.1109/access.2018.2879481 · Cited by 24
“[13].”
Ensemble model for the degradation prediction of proton exchange membrane fuel cell stacks
Wang, F., Huang, C., Mamo, T., & Cheng, X. (2020) · Quality and Reliability Engineering International · doi:10.1002/qre.2718 · Cited by 25
“The details of LSTM in R can be found in the literature.(31) The memory unit structure of LSTM is shown in Figure 2.”
BackgroundProduct Recommendations Enhanced with Reviews
Chelliah, M., & Sarkar, S. (2017) · ACM Conference on Recommender Systems (RecSys) · doi:10.1145/3109859.3109936 · Cited by 23
“More recently, vector representations of words and text segments have been used [4, 15] in order to cluster the contexts of feature mentions.”
MethodDomain-Invariant Feature Distillation for Cross-Domain Sentiment Classification
Hu, M., Wu, Y., Zhao, S., Guo, H., Cheng, R., & Su, Z. (2019) · Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.18653/v1/d19-1558 · Cited by 25
“• ATAE-LSTM (Wang et al., 2016): It also employs attention.”
InfluentialTowards Explainability in Using Deep Learning for the Detection of Anorexia in Social Media
Amini, H., & Kosseim, L. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-51310-8_21 · Cited by 33
“Wang et al. [26], Lee et al. [11], Lin et al. [13], and Ghaeini et al. [6] have used attention visualization based on attention heat maps.”
MethodSentiment Analysis of Fast Food Companies With Deep Learning Models
Abdalrahman, G. A., & Özyurt, F. (2020) · The Computer Journal · doi:10.1093/comjnl/bxaa131 · Cited by 26
Performance Evaluation of Keyword Extraction Methods and Visualization for Student Online Comments
Liu, F., Huang, X., Huang, W., & Duan, S. X. (2020) · Symmetry · doi:10.3390/sym12111923 · Cited by 23
“Wang et al. [56] used word embedding and LSTM for sentiment classification to explore the deeper semantics of words from short texts in social media.”
Knowledge Distillation with Attention for Deep Transfer Learning of Convolutional Networks
Li, X., Xiong, H., Chen, Z., Huan, J., Liu, J., Xu, C., & Dou, D. (2021) · ACM Transactions on Knowledge Discovery from Data · doi:10.1145/3473912 · Cited by 27
“Wang et al. [53] proposed an attention-based long short-term memory network for aspect-level sentiment classification.”
BackgroundSaliencyBERT: Recurrent Attention Network for Target-Oriented Multimodal Sentiment Classification
Wang, J., Liu, Z., Sheng, V. S., Song, Y., & Qiu, C. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-88010-1_1 · Cited by 33
AB-LaBSE: Uyghur Sentiment Analysis via the Pre-Training Model with BiLSTM
Pei, Y., Chen, S., Ke, Z., Silamu, W., & Guo, Q. (2022) · Applied Sciences · doi:10.3390/app12031182 · Cited by 23
A Dataset and BERT-based Models for Targeted Sentiment Analysis on Turkish Texts
Mutlu, M. M., & Özgür, A. (2022) · Annual Meeting of the Association for Computational Linguistics: Student Research Workshop (ACL SRW) · doi:10.18653/v1/2022.acl-srw.39 · Cited by 23
Sentiment knowledge-induced neural network for aspect-level sentiment analysis
Yan, H., Yi, B., Li, H., & Wu, D. (2022) · Neural Computing and Applications · doi:10.1007/s00521-022-07698-0 · Cited by 25
“For this reason, attention-based long short-term memory with aspect embedding (ATAE-LSTM) [15] allows each aspect to learn a corresponding aspect embedding and integrates aspect representation into each word embedding.”
BackgroundZou, L., Zha, Y., Diao, Y., Tang, C., Gu, W., & Shao, D. (2022) · Water Resources Management · doi:10.1007/s11269-022-03381-0 · Cited by 23
“(2) LSTMa, an attention mechanism (Wang et al. 2016) that was introduced in the LSTM to calculate the weights of each hidden state.”
BackgroundAspect-based sentiment analysis for hotel reviews using an improved model of long short-term memory
Jayanto, R., Kusumaningrum, R., & Wibowo, A. (2022) · International Journal of Advances in Intelligent Informatics · doi:10.26555/ijain.v8i3.691 · Cited by 23
“3, this study uses standard LSTM architecture in [28] as the baseline model.”
MethodDeep Learning for Multi-Aspect Sentiment Analysis of TikTok App using the RNN-LSTM Method
Wahyudi, D., & Sibaroni, Y. (2022) · Building of Informatics Technology and Science (BITS) · doi:10.47065/bits.v4i1.1665 · Cited by 23
Zuheros, C., Martínez‐Cámara, E., Herrera‐Viedma, E., Katib, I. A., & Herrera, F. (2023) · Information Fusion · doi:10.1016/j.inffus.2023.101821 · Cited by 28
Alturayeif, N., Aljamaan, H., & Hassine, J. (2023) · Automated Software Engineering · doi:10.1007/s10515-023-00397-7 · Cited by 28
“• AT-LSTM: LSTM model with a basic attention mechanism (Wang et al. 2016).”
MethodPSAN: Prompt Semantic Augmented Network for aspect-based sentiment analysis
He, Y., Huang, X., Zou, S., & Zhang, C. (2023) · Expert Systems with Applications · doi:10.1016/j.eswa.2023.121632 · Cited by 24
Base on contextual phrases with cross-correlation attention for aspect-level sentiment analysis
Zhu, C., Yi, B., & Luo, L. (2023) · Expert Systems with Applications · doi:10.1016/j.eswa.2023.122683 · Cited by 24
A Hybrid Bio-inspired Fuzzy Feature Selection Approach for Opinion Mining of Learner Comments
Jatain, D., Niranjanamurthy, M., & Dayananda, P. (2024) · SN Computer Science · doi:10.1007/s42979-023-02526-1 · Cited by 23
“Aspect fusion LSTM [70] 78.87% BiGRU + aspect attention [71] 86.9% LSTM + aspect embedding [72] 79.81% Sentic LSTM + target attention [73] 79.47% Sindhu et. al [26] 86.2% Proposed model for opinion mining 92.24%”
InfluentialA Variational Approach to Weakly Supervised Document-Level Multi-Aspect Sentiment Classification
Zeng, Z., Zhou, W., Liu, X., & Song, Y. (2019) · Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (NAACL-HLT) · doi:10.18653/v1/n19-1036 · Cited by 23
Luo, C., Wu, J., Li, J., Wang, J., Xu, W., Ming, Z., Wei, B. W., Li, W., & Zomaya, A. Y. (2020) · ACM Transactions on Internet of Things · doi:10.1145/3375799 · Cited by 23
RetractedMultilingual Sentiment Analysis
Nankani, H., Dutta, H., Shrivastava, H., Krishna, P. V. N. S. R., Mahata, D., & Shah, R. R. (2020) · Algorithms for intelligent systems · doi:10.1007/978-981-15-1216-2_8 · Cited by 26
Transfer Correlation Between Textual Content to Images for Sentiment Analysis
Zhang, K., Zhu, Y., Zhang, W., Zhang, W., & Zhu, Y. (2020) · IEEE Access · doi:10.1109/access.2020.2975036 · Cited by 25
“[22] analyzed sentiment by merging the attention in a multilayer neural network.”
BackgroundBAN-ABSA: An Aspect-Based Sentiment Analysis Dataset for Bengali and Its Baseline Evaluation
Masum, M. A., Ahmed, S. J., Tasnim, A., & Islam, M. S. (2021) · Algorithms for intelligent systems · doi:10.1007/978-981-16-0586-4_31 · Cited by 30
Incorporating explicit syntactic dependency for aspect level sentiment classification
Ke, W., Gao, J., Shen, H., & Cheng, X. (2021) · Neurocomputing · doi:10.1016/j.neucom.2021.05.078 · Cited by 25
Sun, Z., Zheng, S., Zhao, H., Niu, Z., Lu, Y., Pan, Y. F., & Yang, Y. (2021) · IEEE Transactions on Computational Biology and Bioinformatics · doi:10.1109/tcbb.2021.3118916 · Cited by 23
Sentiment analysis based on aspect and context fusion using attention encoder with LSTM
Soni, J., & Mathur, K. (2022) · International Journal of Information Technology · doi:10.1007/s41870-022-00966-1 · Cited by 23
A Deep Learning System for Sentiment Analysis of Service Calls
Jia, Y. (2020) · Workshop on e-Commerce and NLP (ECNLP) · doi:10.18653/v1/2020.ecnlp-1.4 · Cited by 22
Attention Transfer Network for Aspect-level Sentiment Classification
Zhao, F., Wu, Z., & Dai, X. (2020) · International Conference on Computational Linguistics · doi:10.18653/v1/2020.coling-main.70 · Cited by 24
Understand Me, if You Refer to Aspect Knowledge: Knowledge-Aware Gated Recurrent Memory Network
Xing, B., & Tsang, I. W.-H. (2022) · IEEE Transactions on Emerging Topics in Computational Intelligence · doi:10.1109/tetci.2022.3156989 · Cited by 24
“aspect-to-context attention mechanism [9]–[11], [17], [21].”
Boost Spectrum Prediction With Temporal-Frequency Fusion Network via Transfer Learning
Li, K., Li, C., Chen, J., Zhang, Q., Liu, Z., & He, S. (2021) · IEEE Transactions on Mobile Computing · doi:10.1109/tmc.2021.3136941 · Cited by 22
“Attention LSTM [44]: The attention mechanism is introduced for the decoder to handle the temporal correlation.”
BackgroundInfluentialBi-graph attention network for aspect category sentiment classification
Shan, Y., Che, C., Wei, X., Wang, X., Zhu, Y., & Jin, B. (2022) · Knowledge-Based Systems · doi:10.1016/j.knosys.2022.109972 · Cited by 23
Understanding Quality of Products from Customers’ Attitude Using Advanced Machine Learning Methods
Ullah, A., Khan, K., Khan, A., & Ullah, S. (2023) · Computers · doi:10.3390/computers12030049 · Cited by 29
“For aspect-level sentiment analysis, the authors in [53] employed pre-trained Glove vectors as inputs in an attention-based LSTMs model.”
MethodAuletta, F., Kallen, R. W., di Bernardo, M., & Richardson, M. J. (2023) · Scientific Reports · doi:10.1038/s41598-023-31807-1 · Cited by 35
Vehicular Positioning Based on GPS/IMU Data Fusion Aided by V2X Networks
Zhang, L., Zhao, H., Chen, J., Li, L., & Liu, X. (2024) · IEEE Sensors Journal · doi:10.1109/jsen.2024.3355185 · Cited by 22
“In the second step, X scale is imported into an attention mechanism-based LSTM network [25] for GPS/IMU fusion, X scale ∈ R 9 × 1 , in our article, it will be called the ALSTM network, the structure of which is shown in Fig.”
MethodData Shunt: Collaboration of Small and Large Models for Lower Costs and Better Performance
Dong, C., Zhuang, Y., Zhang, S., Liu, J., Dong, S., & Tang, S. (2024) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v38i10.29003 · Cited by 44
“We follow (Xu et al. 2015) to design the small model, where the encoder is a ResNet-101, and the decoder is an LSTM.”
MethodInfluentialAspect-based sentiment analysis with multi-granularity information mining and sentiment hint
Gu, T., He, Z., Hui, Z., Li, M., & Ying, D. (2024) · Expert Systems with Applications · doi:10.1016/j.eswa.2024.124104 · Cited by 22
Li, Q., Wen, W., & Qin, J. (2024) · Neural Networks · doi:10.1016/j.neunet.2024.106381 · Cited by 22
Neural multi-task learning for end-to-end Arabic aspect-based sentiment analysis
Bensoltane, R., & Zaki, T. (2024) · Computer Speech & Language · doi:10.1016/j.csl.2024.101683 · Cited by 25
Stochastic Tokenization with a Language Model for Neural Text Classification
Hiraoka, T., Shindo, H., & Matsumoto, Y. (2019) · Proceedings of the conference - Association for Computational Linguistics. Meeting · doi:10.18653/v1/p19-1158 · Cited by 34
“Then, the token embeddings are looked up and fed into a neural network encoder such as a feed-forward neural network (Iyyer et al., 2015), a convolutional neural network (CNN) (Kim, 2014; Kalchbrenner et al., 2014), or a long short-term memory (LSTM) network (Wang et al., 2016a,b).”
MethodHypergraph Label Propagation Network
Zhang, Y., Wang, N., Chen, Y., Zou, C., Wan, H., Zhao, X., & Gao, Y. (2020) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v34i04.6170 · Cited by 22
“Deep learning methods have benefited from large-scale labeled datasets and have shown great superiority in many application scenario such as visual object detection (He et al. 2016), natural language understanding (Wang et al. 2016), etc .”
BackgroundLiang, B., Yin, R., Gui, L., Du, J., He, Y., & Xu, R. (2020) · ACM International Conference on Information and Knowledge Management (CIKM) · doi:10.1145/3340531.3411868 · Cited by 27
“Thanks in part to the availability of copious annotated resources for some aspects, recent attention-based models can effectively distinguish the sentiment polarities of different aspects in the same sentence [9, 17, 40].”
InfluentialMukherjee, R., Shetty, S., Chattopadhyay, S., Maji, S., Datta, S., & Goyal, P. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-72240-1_7 · Cited by 29
“For the memory network based models, on the other hand, the variability is not so low, and the corresponding scores have been shown in Table 5 (b) in the order (ATAE-LSTM, IAN, RAM).”
MethodInfluentialChandra, J. K., Cambria, E., & Nanetti, A. (2020) · IEEE ... International Conference on Data Mining workshops · doi:10.1109/icdmw51313.2020.00011 · Cited by 22
“GCNN is also less complex and more efficient than recurrent network-based models [48] [49].”
BackgroundOr-Meir, O., Cohen, A., Elovici, Y., Rokach, L., & Nissim, N. (2021) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn52387.2021.9533481 · Cited by 22
“Other prior studies have has applied attention mechanisms for various problems, such as text translation, sentiment analysis, and image captioning [18]–[20].”
BackgroundHu, G., Lu, G., & Zhao, Y. (2021) · Findings of the Association for Computational Linguistics: EMNLP (Findings of EMNLP) · doi:10.18653/v1/2021.findings-emnlp.51 · Cited by 33
“Mining the causes of certain emotion has a wide range of applications, such as public opinion monitoring and product review mining (Wang et al., 2016; Tang et al., 2016; Ma et al., 2017; Xia et al., 2019; Phan ∗Corresponding author. and Ogunbona, 2020; Ding et al., 2020).”
BackgroundAkter, M. S., Shahriar, H., Chowdhury, R., & Mahdy, M. R. C. (2022) · Future Internet · doi:10.3390/fi14090252 · Cited by 23
A review of artificial intelligence for sports: Technologies and applications
Li, W., Liu, M., Liu, J., Zhang, B., Yu, T., Guo, Y., & Dai, Q. (2025) · Intelligent Sports and Health · doi:10.1016/j.ish.2025.05.001 · Cited by 27
LEAN-LIFE: A Label-Efficient Annotation Framework Towards Learning from Explanation
Lee, D., Khanna, R., Lin, B. Y., Lee, S., Ye, Q., Boschee, E., Neves, L., & Ren, X. (2020) · Annual Meeting of the Association for Computational Linguistics: System Demonstrations (ACL Demo) · doi:10.18653/v1/2020.acl-demos.42 · Cited by 27
Enhancing LSTM Models with Self-attention and Stateful Training
Katrompas, A., & Metsis, V. (2021) · Lecture notes in networks and systems · doi:10.1007/978-3-030-82193-7_14 · Cited by 29
“Attention is essentially a neural network within a neural network , which is learning to weigh portions of a sequence for relative feature importance [27, 30].”
BackgroundPG-RNN: using position-gated recurrent neural networks for aspect-based sentiment classification
Bai, Q., Zhou, J., & He, L. (2021) · The Journal of Supercomputing · doi:10.1007/s11227-021-04019-5 · Cited by 23
“Wang et al. [17] designed an attention-based LSTM to concentrate on different parts of a sentence when different targets were taken as inputs to explore the potential correlation of targets and sentiment polarities in aspect-based sentiment classification.”
BackgroundMethodResume Parsing based on Multi-label Classification using Neural Network models
Liu, J., Shen, Y., Zhang, Y., & Krishnamoorthy, S. (2021) · International Conference on Big Data and Computing (ICBDC) · doi:10.1145/3469968.3469998 · Cited by 21
“Attention mechanism originates from human research on visual image information that uses limited resources to represent the whole thing rationally [18].”
BackgroundCASA: Conversational Aspect Sentiment Analysis for Dialogue Understanding
Song, L., Xin, C., Lai, S., Wang, A., Su, J., & Xu, K. (2022) · Journal of Artificial Intelligence Research · doi:10.1613/jair.1.12802 · Cited by 27
“In addition, the existing work on SATA (Nguyen and Shirai, 2015; Ruder et al., 2016; Wang et al., 2016; Chen et al., 2017; Wang et al., 2017; Li et al., 2019; Luo et al., 2019) typically follows the assumption that product reviews are usually aspect centric, and that each aspect corresponds to one…”
BackgroundAkter, M. S., Shahriar, H., Ahmed, N., & Cuzzocrea, A. (2022) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata55660.2022.10020249 · Cited by 23
“2) BiLSTM: The Bidirectional Long short-term memory (BiLSTM) was first proposed by GRAVES [34].”
BackgroundRank-Aware Negative Training for Semi-Supervised Text Classification
Ahmed, M., Pan, S., Bo, W., Su, J., Cao, X., Zhang, W., & Liu, Y. (2023) · Transactions of the Association for Computational Linguistics · doi:10.1162/tacl_a_00574 · Cited by 24
“…a deep memory or an attention mechanism to learn semantic representation in response to a given category (Socher et al., 2013b; Zhang et al., 2015; Wang et al., 2016; Ma et al., 2017; Chen et al., 2017; Johnson and Zhang, 2017; Conneau et al., 2017; Song et al., 2019; Murtadha et al., 2020; Tsai…”
BackgroundSaid, A., & Göker, H. (2023) · Cognitive Neurodynamics · doi:10.1007/s11571-023-10010-y · Cited by 23
“Moreover, i t represents the value of I , f t the value of f, and o t the value of o and c at the moment t (Liu and Guo 2019; Wang et al. 2016).”
Tran, V. N., Ivanov, V. Y., & Kim, J. (2023) · Advances in Water Resources · doi:10.1016/j.advwatres.2023.104569 · Cited by 21
Akter, M. S., Shahriar, H., Cuzzocrea, A., Wu, F., & Rodriguez-Cardenas, J. (2023) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata59044.2023.10386719 · Cited by 23
“2) The Bidirectional Long Short-Term Memory (BiLSTM): BiLSTM, a type of RNN introduced by GRAVES [32], excels in sequence-based multi-class classification tasks.”
MethodZhao, C., Wu, M., Yang, X., Sun, X., Wang, S., & Li, D. (2024) · ACM Transactions on Asian and Low-Resource Language Information Processing · doi:10.1145/3653299 · Cited by 24
Large Language Models for Metaphor Detection: Bhagavad Gita and Sermon on the Mount
Chandra, R., Tiwari, A., Jain, N., & Badhe, S. (2024) · IEEE Access · doi:10.1109/access.2024.3411060 · Cited by 24
“Attention-based mechanisms inspired by biological cognitive systems have further improved LSTM models for NLP applications [40], [92].”
BackgroundFu, J., Li, X., Zhu, Y., Du, Y., Fan, Y., Chen, X., Huang, D., & Wang, S. (2024) · Applied Soft Computing · doi:10.1016/j.asoc.2024.112233 · Cited by 21
Zhang, Y., Xu, H., Zhang, D., & Xu, R. (2024) · Electronics · doi:10.3390/electronics13183724 · Cited by 24
“Early methodologies primarily employed LSTM networks to learn contextual representations of sentences and incorporated attention mechanisms to model the interactions between aspect terms and their contexts [12–15].”
BackgroundMoore, A., & Rayson, P. (2017) · International Workshop on Semantic Evaluation (SemEval) · doi:10.18653/v1/s17-2095 · Cited by 21
“Future work will be to implement aspect specific information into an LSTM model as it has been shown to be useful in other work (Wang et al., 2016).”
MethodComparative Study of CNN and LSTM based Attention Neural Networks for Aspect-Level Opinion Mining
Quan, W., Chen, Z., Gao, J., & Hu, X. T. (2018) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata.2018.8622150 · Cited by 21
“The dimension of word embeddings is 300 as in previous studies [17], [20].”
MethodResultInfluentialEntity Linking via Symmetrical Attention-Based Neural Network and Entity Structural Features
Hu, S., Tan, Z., Zeng, W., Ge, B., & Xiao, W. (2019) · Symmetry · doi:10.3390/sym11040453 · Cited by 21
“* Existing DNN models omit the word order in mention and candidate entities’ contexts, which has proven to be pivotal for natural language understanding [30].”
Learning to Detect Opinion Snippet for Aspect-Based Sentiment Analysis
Hu, M., Zhao, S., Guo, H., Cheng, R., & Su, Z. (2019) · Conference on Computational Natural Language Learning · doi:10.18653/v1/k19-1091 · Cited by 22
“com/huggingface/pytorch-pretrainedBERT • AT-LSTM (Wang et al., 2016): it utilizes the attention mechanism to produce an aspect-specific sentence representation.”
BackgroundMethodInfluentialStructured Self-Attention Weights Encode Semantics in Sentiment Analysis
Wu, Z., Nguyen, T.-S., & Ong, D. C. (2020) · BlackboxNLP Workshop on Analyzing and Interpreting Neural Networks for NLP (BlackboxNLP) · doi:10.18653/v1/2020.blackboxnlp-1.24 · Cited by 29
A Joint Model for Aspect-Category Sentiment Analysis with Shared Sentiment Prediction Layer
Li, Y., Yang, Z., Yin, C., Xu, P., Cui, L., Huang, Q., & Wei, T. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-63031-7_28 · Cited by 27
“However, most existing methods (Zhou et al., 2015; Movahedi et al., 2019; Wang et al., 2016; Ruder et al., 2016; Cheng et al., 2017; Xue and Li, 2018; Tay et al., 2018) divide the ACSA task into two subtasks: aspect category detection (ACD) which detects aspect categories in a text and sentiment…”
MethodInfluential
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.