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 901–1,000 of 1,003
Attention Aware Bidirectional Gated Recurrent Unit Based Framework for Sentiment Analysis
Tian, Z., Rong, W., Shi, L., Liu, J., & Xiong, Z. (2018) · Lecture notes in computer science · doi:10.1007/978-3-319-99365-2_6 · Cited by 16
Using Bidirectional Long Short Term Memory with Attention Layer to Estimate Driver Behavior
Kouchak, S. M., & Gaffar, A. (2019) · International Conference on Machine Learning and Applications · doi:10.1109/icmla.2019.00059 · Cited by 18
“The original attention mechanism made a significant enhancement in language translation applications compared to other deep learning methods such as encoder decoder LSTM network [46].”
MethodA BERT-based Hierarchical Model for Vietnamese Aspect Based Sentiment Analysis
Tran, O., & Bui, V. T. (2020) · International Conference on Knowledge and Systems Engineering/Proceedings · doi:10.1109/kse50997.2020.9287650 · Cited by 18
An Overview on Fine-grained Text Sentiment Analysis: Survey and Challenges
Guo, X., Yu, W., & Wang, X. (2021) · Journal of Physics Conference Series · doi:10.1088/1742-6596/1757/1/012038 · Cited by 16
“The basic combination of long-term and short-term memory networks and attention mechanisms became popular due to their ability of capturing long-distance and important information[29][30][31][32].”
BackgroundTargets and Aspects in Social Media Hate Speech
Shvets, A., Fortuna, P., Juan Soler-Company, & Wanner, L. (2021) · Workshop on Online Abuse and Harms (WOAH) · doi:10.18653/v1/2021.woah-1.19 · Cited by 16
“The encoder is a stacked bidirectional LSTM, while the decoder is a stacked unidirectional LSTM (Hochreiter and Schmidhuber, 1997).”
BackgroundIntelligent Vehicles Trajectory Prediction with Spatial and Temporal Attention Mechanism
Meng, Q., Shang, B., Liu, Y., Guo, H., & Zhao, X. (2021) · IFAC-PapersOnLine · doi:10.1016/j.ifacol.2021.10.204 · Cited by 16
Towards Unifying the Label Space for Aspect- and Sentence-based Sentiment Analysis
Zhang, Y., Zhang, M., Wu, S., & Zhao, J. (2022) · Findings of the Association for Computational Linguistics: ACL (Findings of ACL) · doi:10.18653/v1/2022.findings-acl.3 · Cited by 24
Aspect-based sentiment analysis with enhanced aspect-sensitive word embeddings
Qi, Y., Zheng, X., & Huang, X. (2022) · Knowledge and Information Systems · doi:10.1007/s10115-022-01688-3 · Cited by 16
Contextual Graph Attention Network for Aspect-Level Sentiment Classification
Miao, Y., Luo, R., Zhu, L., Liu, T., Zhang, W., Cai, G., & Zhou, M. Q. (2022) · Mathematics · doi:10.3390/math10142473 · Cited by 16
A Multi-Task Dual-Encoder Framework for Aspect Sentiment Triplet Extraction
Huan, H., He, Z., Xie, Y., & Guo, Z. (2022) · IEEE Access · doi:10.1109/access.2022.3210180 · Cited by 16
“The ASC task aims to classify the sentiment polarity of the aspect terms.”
BackgroundMethodInfluentialSentiment Recognition of Hinglish Code Mixed Data using Deep Learning Models based Approach
Das, S., & Singh, T. (2023) · International Conference on Cloud Computing, Data Science & Engineering (Confluence) · doi:10.1109/confluence56041.2023.10048879 · Cited by 16
“(BiLSTM): Applications for text categorization have used it to capture the context with success [27].”
BackgroundMulti-Task Learning Model with Data Augmentation for Arabic Aspect-Based Sentiment Analysis
Fadel, A. S., Abulnaja, O. A., & Saleh, M. (2023) · Computers, materials & continua/Computers, materials & continua (Print) · doi:10.32604/cmc.2023.037112 · Cited by 19
DigNet: Digging Clues From Local–Global Interactive Graph for Aspect-Level Sentiment Classification
Xing, B., & Tsang, I. W.-H. (2025) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2025.3564306 · Cited by 17
“In these models, the most common way to model the aspectcontext interactions is attention mechanism (Wang et al., 2016; Ma, Li, Zhang, & Wang, 2017; Chen, Sun, Bing, & Yang, 2017; Tang, Lu, Su, Ge, Song, Sun, & Luo, 2019; Xing, Liao, Song, Wang, Zhang, Wang, & Huang, 2019).”
TreeNet: Learning Sentence Representations with Unconstrained Tree Structure
Cheng, Z., Yuan, C., Li, J., & Yang, H. (2018) · International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2018/557 · Cited by 16
“…sequence models have been witnessed the resurge of recurrent networks in natural language processing (NLP) applications, such as text classification [Wang et al. , 2016; Zhang et al. , 2017], machine translation [Sutskever et al. , 2014], question answering [Wang and Nyberg, 2015] and so on.”
BackgroundZhong, G., Lin, X., Chen, K., Li, Q., & Huang, K. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-39431-8_5 · Cited by 17
On document representations for detection of biased news articles
Cruz, A. F., Rocha, G., & Cardoso, H. L. (2020) · ACM Symposium on Applied Computing · doi:10.1145/3341105.3374025 · Cited by 16
“extraction [43], and sentiment analysis [61].”
Predicting Emotion Reactions for Human–Computer Conversation: A Variational Approach
Zhang, R., Wang, Z., Huang, Z., Li, L., & Zheng, M. (2021) · IEEE Transactions on Human-Machine Systems · doi:10.1109/thms.2020.3044975 · Cited by 16
Affective awareness in neural sentiment analysis
Xiang, R., Li, J., Wan, M., Gu, J., Lu, Q., Li, W., & Huang, C. (2021) · Knowledge-Based Systems · doi:10.1016/j.knosys.2021.107137 · Cited by 16
Srividya, K., & Sowjanya, A. M. (2021) · Materials Today Proceedings · doi:10.1016/j.matpr.2021.01.782 · Cited by 16
RetractedGame Theory and Machine Learning in UAVs-Assisted Wireless Communication Networks: A SurveyPreprint
Zhou, M., Guan, Y., Hayajneh, M., Niu, K., & Abdallah, C. T. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2108.03495 · Cited by 21
“LSTM networks have been successfully used in classification, image recognition, and machine translation fields [78, 79, 80].”
MethodOuerhani, N., Maalel, A., & Ghézala, H. B. (2022) · Cluster Computing · doi:10.1007/s10586-022-03601-7 · Cited by 15
TS-GCN: Aspect-level sentiment classification model for consumer reviews
Zhang, S., Zhao, T., Wu, H., Zhu, G., & Li, K. (2022) · Computer Science and Information Systems · doi:10.2298/csis220325052z · Cited by 17
Jiang, B., Xu, G., & Liu, P. (2023) · The Journal of Supercomputing · doi:10.1007/s11227-022-05002-4 · Cited by 15
“To learn contextual information for a given sentence, most early works [3, 4] utilize long-short-term memory (LSTM) [5] models to model the context of a given aspect word.”
BackgroundMethodInfluentialDual-interest Factorization-heads Attention for Sequential Recommendation
Lin, G., Gao, C., Zheng, Y., Chang, J., Niu, Y., Song, Y., Li, Z., Jin, D., & Li, Y. (2023) · International World Wide Web Conference (WWW) · doi:10.1145/3543507.3583278 · Cited by 24
“Attention mechanisms are often explainable and have been widely used in deep models to illustrate the learned representation by visualizing the distribution of attention scores or weights under specifc inputs [4, 21, 35].”
BackgroundZangene, A. R., Samuel, O. W., Abbasi, A., McEwan, A. A., Asogbon, M. G., Li, G., & Nazarpour, K. (2023) · Biomedical Signal Processing and Control · doi:10.1016/j.bspc.2023.105103 · Cited by 18
A Sparse Self-Attention Enhanced Model for Aspect-Level Sentiment Classification
Dhanith, P. R. J., Surendiran, B., Rohith, G., Kanmani, R. S., & Devi, K. V. (2024) · Neural Processing Letters · doi:10.1007/s11063-024-11513-3 · Cited by 15
A Pre-Trained Model for Aspect-based Sentiment Analysis Task: using Online Social Networking
Chauhan, A., Sharma, A., & Mohana, R. (2024) · Procedia Computer Science · doi:10.1016/j.procs.2024.03.193 · Cited by 15
A syntactic features and interactive learning model for aspect-based sentiment analysis
Zou, W., Zhang, W., Tian, Z., & Wu, W. (2024) · Complex & Intelligent Systems · doi:10.1007/s40747-024-01449-5 · Cited by 15
A Hybridized Approach for Enhanced Fake Review Detection
Xu, S., Cuan, H., Yin, Z., & Yin, C. (2024) · IEEE Transactions on Computational Social Systems · doi:10.1109/tcss.2024.3411635 · Cited by 15
“Moreover, a certain part of the review text is often more relevant to the target task [38].”
Su, H., Wang, X., Li, J., Xie, S., & Luo, X. (2024) · IEEE Transactions on Computational Social Systems · doi:10.1109/tcss.2024.3368171 · Cited by 19
“Traditional attention-based methods [7], [8], [9], [13] learn the aspect-related semantic information with the self-attention.”
MethodSuresh, S., & Banu, K. S. (2024) · IEEE Access · doi:10.1109/access.2024.3471816 · Cited by 17
“Wang et al. in [21] suggested including aspect embedding and an aspect to the sentence attention mechanism, along with LSTM and thus ATAE-LSTM was proposed.”
BackgroundCo-attention Networks for Aspect-Level Sentiment Analysis
Li, H., Xue, Y., Zhao, H., Hu, X., & Peng, S. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-32236-6_17 · Cited by 15
“Baselines LSTM 74.30 66.50 66.50 TD-LSTM [16] 75.60 68.10 70.80 ATAE-LSTM [7] 77.20 68.70 - MemNet [17] 78.16 70.33 68.50 IAN [2] 78.60 72.10 - RAM [18] 80.23 74.49 69.36 AOA-LSTM [8] 81.20 74.50 - LCR-Rot [9] 81 Among all the baseline models, LSTM shows the lowest accuracy than any other methods,…”
BackgroundInfluentialTang, X., Shen, X., Wang, Y., & Yu-juan, Y. (2020) · Lecture notes in computer science · doi:10.1007/978-3-030-63031-7_22 · Cited by 24
“The attention mechanism is further introduced to model the target-context association [Wang et al.2016].”
MethodSelf-citationWu, H., Wang, Z., Qing, F., & Li, S. (2021) · Electronics · doi:10.3390/electronics10030270 · Cited by 15
Out of Context: A New Clue for Context Modeling of Aspect-based Sentiment Analysis
Xing, B., & Tsang, I. W.-H. (2022) · Journal of Artificial Intelligence Research · doi:10.1613/jair.1.13410 · Cited by 15
“As for the context encoder, LSTM is the most widely-used context encoder because of its advantages for sequence modeling (Tang, Qin, Feng, & Liu, 2016a; Ma et al., 2017; Devamanyu et al., 2018; Wang et al., 2016; Tay et al., 2018; Liu & Zhang, 2017; Yang, Tu, Wang, Xu, & Chen, 2017; He, Lee, Ng, & Dahlmeier, 2018).”
BackgroundMethodResultInfluentialA Novel Matrix Profile-Guided Attention LSTM Model for Forecasting COVID-19 Cases in USA
Liu, Q., Fung, D. L. X., Lac, L., & Hu, P. (2021) · Frontiers in Public Health · doi:10.3389/fpubh.2021.741030 · Cited by 15
“Recently, the attention mechanism in machine learning was developed to overcome this limitation (35).”
BackgroundAspect Feature Distillation and Enhancement Network for Aspect-based Sentiment Analysis
Liu, R., Cao, J., Sun, N., & Jiang, L. (2022) · International ACM SIGIR Conference on Research and Development in Information Retrieval (SIGIR) · doi:10.1145/3477495.3531938 · Cited by 17
“[43] encoded sentences and given aspect words with LSTM, processed the hidden layer output with attention mechanism, and obtained the sentiment polarity representation of aspect words.”
BackgroundMulti-Channel Convolutional Neural Network for the Identification of Eyewitness Tweets of Disaster
Kumar, A., Singh, J. P., Rana, N. P., & Dwivedi, Y. K. (2022) · Information Systems Frontiers · doi:10.1007/s10796-022-10309-x · Cited by 15
“The attention-based techniques performed well in several natural language-processing tasks (Yang et al., 2016; Wang et al., 2016) that motivated us to use this technique with RNN, GRU, and LSTM networks.”
MethodA KGE Based Knowledge Enhancing Method for Aspect-Level Sentiment Classification
Yu, H., Lu, G., Cai, Q., & Xue, Y. (2022) · Mathematics · doi:10.3390/math10203908 · Cited by 15
EIAASG: Emotional Intensive Adaptive Aspect-Specific GCN for sentiment classification
Arumugam, C., & Nallaperumal, K. (2022) · Knowledge-Based Systems · doi:10.1016/j.knosys.2022.110149 · Cited by 15
EDU-Capsule: aspect-based sentiment analysis at clause level
Lin, T., Sun, A., & Wang, Y. (2022) · Knowledge and Information Systems · doi:10.1007/s10115-022-01797-z · Cited by 17
Self-citationCHIHAB, M., Chiny, M., Mabrouk, N., BOUSSATTA, H., CHIHAB, Y., & Hadi, M. Y. (2022) · International Journal of Advanced Computer Science and Applications · doi:10.14569/ijacsa.2022.0131052 · Cited by 17
Wang, J., Li, X., & An, X. (2022) · Complex & Intelligent Systems · doi:10.1007/s40747-022-00940-1 · Cited by 17
“We use ASGCN and AEGCN as our main baseline models, and we also compare our proposed model (MFLGCN) with the following methods: • ATAE-LSTM [1] combines aspect embedding and attention mechanism to ABSA.”
BackgroundMethodInfluentialA Contrastive Learning Framework with Tree-LSTMs for Aspect-Based Sentiment Analysis
Zhang, Q., Wang, S., & Li, J. (2023) · Neural Processing Letters · doi:10.1007/s11063-023-11181-9 · Cited by 15
Hao, S., Yao, J., Shi, C., Yu, Z., Xu, S., Li, D., & Cheng, Y. (2023) · Entropy · doi:10.3390/e25060878 · Cited by 15
POS-ATAEPE-BiLSTM: an aspect-based sentiment analysis algorithm considering part-of-speech embedding
Zhao, Q., Mo, Z., & Fan, M. (2023) · Applied Intelligence · doi:10.1007/s10489-023-04952-3 · Cited by 15
“Based on the abovementioned information, the baseline models are listed as follows: (1) ATAE-LSTM [37]: The embedding layer of ATAE-LSTM contains text embedding and aspect word embedding.”
MethodInfluentialAspect-Based Sentiment Analysis Using Local Context Focus Mechanism with DeBERTa
Zhao, T., Du, J., Shao, Y., & Li, A. (2023) · International Conference on Data-driven Optimization of Complex Systems (DOCS) · doi:10.1109/docs60977.2023.10294548 · Cited by 19
“ATAE-LSTM [45] is a classic LSTM based model, which uses attention-based LSTM to explore the relationship between an aspect and sentence content.”
MethodInfluentialFew-Shot Learning for Chinese Legal Controversial Issues Classification
Yin, F., Tian, X., Wu, H., Gu, S., Wang, Z., Wang, F., Li, J., & Weng, Y. (2020) · IEEE Access · doi:10.1109/access.2020.2988493 · Cited by 15
“Text classification technology has been successfully used to achieve state-ofthe-art performance in a variety of applications such as spam recognition [8], sentiment analysis [9] and public opinion monitoring [10].”
MethodEDLLIE-Net: Enhanced Deep Convolutional Networks for Low-Light Image Enhancement
Ke, X., Lin, W., Chen, G., Chen, Q., Qi, X., & Ma, J. (2020) · International Conference on Image, Vision and Computing (ICIVC) · doi:10.1109/icivc50857.2020.9177454 · Cited by 17
Prediction of tourist flow based on multi‐source traffic data in scenic spot
Lu, H., Zhang, J., Xu, Z., Shi, R., Wang, J., & Xu, S. (2020) · Transactions in GIS · doi:10.1111/tgis.12724 · Cited by 17
“For instance, Wang, Huang, Zhao, and Zhu (2016) proposed an attention-based LSTM network for aspect-level sentiment classification.”
BackgroundEnhancing trajectory prediction using sparse outputs: application to team sports
Victor, B., Nibali, A., He, Z., & Carey, D. L. (2021) · Neural Computing and Applications · doi:10.1007/s00521-021-05888-w · Cited by 15
“Several recent works in trajectory prediction have utilised recurrent neural network (RNN) architectures such as long short-term memory (LSTM) and gated recurrent unit (GRU) models [1, 2] due to their success in language modelling [14, 33], machine translation [31, 34] and sentiment analysis [38].”
BackgroundSentiment Analysis Method of Network Text Based on Improved AT-BiGRU Model
Lu, X., & Zhang, H. (2021) · Scientific Programming · doi:10.1155/2021/6669664 · Cited by 22
“[27] combined LSTM and attention mechanism to propose an ATAE aspect sentiment analysis model.”
BackgroundMEAN: Multi-head Entity Aware Attention Networkfor Political Perspective Detection in News Media
Li, C., & Goldwasser, D. (2021) · Workshop on Natural Language Processing for Internet Freedom: Censorship, Disinformation, and Propaganda (NLP4IF) · doi:10.18653/v1/2021.nlp4if-1.10 · Cited by 15
“Many neural network based approaches have been proposed (Wang et al., 2016; Chen et al., 2017; Fan et al., 2018) to incorporate the aspect term into the text model.”
BackgroundALBERTC-CNN Based Aspect Level Sentiment Analysis
Ye, X., Xu, Y., & Luo, M. (2021) · IEEE Access · doi:10.1109/access.2021.3094026 · Cited by 16
“, 2016): The MemNet model [23] uses a multi-hop attention network to represent the feature vector of the text, so themodel can capture the important word information in the text.”
MethodBidirectional-GRU Based on Attention Mechanism for Aspect-level Sentiment Analysis
Zhai, P., & Dingyi, Z. (2019) · International Conference on Machine Learning and Computing (ICMLC) · doi:10.1145/3318299.3318368 · Cited by 15
“Aspect-level sentiment analysis is a fine-grained task [3], to analysis the specific emotional polarity in a given text or sentence.”
BackgroundDuran-Vega, M. A., González-Mendoza, M., Chang, L., & Suárez-Ramírez, C. D. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2111.08867 · Cited by 15
“As result, approaches like attention modules have become popular in RNNs [9, 6, 10], which allow models to focus on certain information and improve their results.”
A complete framework for aspect-level and sentence-level sentiment analysis
Chiha, R., Ayed, M. B., & Pereira, C. D. C. (2022) · Applied Intelligence · doi:10.1007/s10489-022-03279-9 · Cited by 14
“Its effectiveness was demonstrated in various NLP research fields such as machine translation [62], relation classification [63], Named Entity Recognition [64, 65], sentiment analysis at aspect-level [25–27 , 66– 68 ] as well as Firstly, we defined an embedding layer of opinion words.”
BackgroundHyper Parameter Optimization of Stack LSTM Based Regression for PM 2.5 Data in Bangkok
Pattana-Anake, V., & Joseph, F. J. J. (2022) · International Conference on Business and Industrial Research (ICBIR) · doi:10.1109/icbir54589.2022.9786465 · Cited by 14
Abbas, S., Boulila, W., Driss, M., Victor, N., Sampedro, G. A., Abisado, M., & Gadekallu, T. R. (2023) · IEEE Transactions on Consumer Electronics · doi:10.1109/tce.2023.3323334 · Cited by 15
“The attention-focused LSTM was proposed by Wang et al. in 2016 [12].”
BackgroundMethodBeyond geofencing: Behavior detection using AIS
Sturgis, R., Emiya, V., Couëtoux, B., & Garreau, P. (2024) · Ocean Engineering · doi:10.1016/j.oceaneng.2023.116630 · Cited by 15
Research on the "shape-performance-control" integrated digital twin system for boom-type roadheaders
Zhang, J., Wan, C., Wang, J., Chen, C., Wang, T., Zhang, R., & Guo, H. (2024) · Scientific Reports · doi:10.1038/s41598-024-56539-8 · Cited by 14
Twin Towers End to End model for aspect-based sentiment analysis
Li, Z., Song, Y., Lu, X., & Liu, M. (2024) · Expert Systems with Applications · doi:10.1016/j.eswa.2024.123713 · Cited by 14
Aspect based sentiment analysis using fine-tuned BERT model with deep context features
Rajan, A., & Manur, M. (2024) · IAES International Journal of Artificial Intelligence · doi:10.11591/ijai.v13.i2.pp1250-1261 · Cited by 14
“- Attention based long sort term meory (ATAE-LSTM) [24]: It is an extended version of LSTM architecture, once aspect embedding and word embedding is passed through LSTM architecture, hidden states are mapped and the attention vector is computed after combining the hidden states.”
Pradeepa, S., Jomy, E., Vimal, S., Hassan, M. M., Dhiman, G., Karim, A., & Kang, D. (2024) · Scientific Reports · doi:10.1038/s41598-024-70565-6 · Cited by 14
Aspect-based sentiment analysis via bidirectional variant spiking neural P systems
Zhu, C., Yi, B., & Luo, L. (2024) · Expert Systems with Applications · doi:10.1016/j.eswa.2024.125295 · Cited by 16
GSMNet: Global Semantic Memory Network for Aspect-Level Sentiment Classification
Liu, Z., Wang, J., Du, X. X., Rao, Y., & Quan, X. (2020) · IEEE Intelligent Systems · doi:10.1109/mis.2020.3042253 · Cited by 14
METNet: A Mutual Enhanced Transformation Network for Aspect-based Sentiment Analysis
Jiang, B., Hou, J., Zhou, W., Yang, C., Wang, S., & Pang, L. (2020) · International Conference on Computational Linguistics · doi:10.18653/v1/2020.coling-main.14 · Cited by 16
“AE-LSTM (Wang et al., 2016) : AE-LSTM is an attention-based LSTM network, which uses the attention mechanism to calculate the correlation between aspect and words in sentence.”
BackgroundMethodInfluentialMulti-Grained Attention Representation With ALBERT for Aspect-Level Sentiment Classification
Chen, Y., Kong, L., Wang, Y., & Kong, D. (2021) · IEEE Access · doi:10.1109/access.2021.3100299 · Cited by 14
“The final sentence representation is the sum of the weights of the hidden vector [32].”
BackgroundMethodSelf-citationDeep Learning Applications on Cybersecurity
Lago, C., Romón, R., Pastor-López, I., Sanz, B., Tellaeche, A., & Bringas, P. G. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-86271-8_51 · Cited by 15
Do You Brush Your Teeth Properly? An Off-body Sensor-based Approach for Toothbrushing Monitoring
Hussain, Z., Waterworth, D., Aldeer, M. M. N., Zhang, W. E., Sheng, Q. Z., & Ortiz, J. (2021) · IEEE International Conference on Digital Health (ICDH) · doi:10.1109/icdh52753.2021.00018 · Cited by 20
Modeling Tweet Dependencies with Graph Convolutional Networks for Sentiment Analysis
Keramatfar, A., Amirkhani, H., & Bidgoly, A. J. (2022) · Cognitive Computation · doi:10.1007/s12559-021-09986-8 · Cited by 14
“Recently, Zhang et al. [67] used Bidirectional Encoder Representation from Transformers (BERT) with Bidirectional LSTM (BiLSTM) and Conditional Random Field (CRF) layers on top of BERT to model the sequence of tweets.”
MethodFedKC: Federated Knowledge Composition for Multilingual Natural Language Understanding
Wang, H., Zhao, H., Wang, Y., Yu, T., Gu, J., & Gao, J. (2022) · International World Wide Web Conference (WWW) · doi:10.1145/3485447.3511988 · Cited by 28
“paraphrase identification [21, 56, 57], natural language inference [30, 33, 37, 51], question answering [2, 5, 7, 55], news classification [6, 18], sentiment classification [45, 46, 52] and so on.”
BackgroundSelf-citationDeep Learning-Based Sentiment Analysis on COVID-19 News Videos
Varghese, M., & Anoop, V. S. (2022) · Lecture notes in networks and systems · doi:10.1007/978-981-16-7618-5_20 · Cited by 18
A novel selective learning based transformer encoder architecture with enhanced word representation
Ansar, W., Goswami, S., Chakrabarti, A., & Chakraborty, B. (2022) · Applied Intelligence · doi:10.1007/s10489-022-03865-x · Cited by 16
“, 2016 [10] developed a LSTM model with attention mechanism for aspect-sentiment classification namely, ATAE LSTM.”
BackgroundMethodInfluentialZheng, J., Liao, J., & Chen, Z. (2022) · Sensors · doi:10.3390/s22176489 · Cited by 15
“Since the output of the last time step of the LSTM network in C/D-FUSA was used for the fault diagnosis, the attention module based on time series was unavailable [43].”
MethodDeep Neural Networks for Location Reference Identification From Bilingual Disaster-Related Tweets
Kumar, A., & Singh, J. P. (2022) · IEEE Transactions on Computational Social Systems · doi:10.1109/tcss.2022.3213702 · Cited by 14
“Several natural language processing tasks [57], [58] successfully utilized attention-based networks to achieve better performance.”
MethodWang, D., Liang, Y., Ma, H., & Xu, F. (2023) · Applied Sciences · doi:10.3390/app13053016 · Cited by 16
Improved Feature Representation Using Collaborative Network for Cross-Domain Sentiment Analysis
Gunasekar, M., & Thilagamani, S. (2023) · Information Technology And Control · doi:10.5755/j01.itc.52.1.32119 · Cited by 14
Aspect-Based Sentiment Analysis Using Adversarial BERT with Capsule Networks
Yang, P., Zhang, P., Li, B., Ji, S., & Yi, M. (2023) · Neural Processing Letters · doi:10.1007/s11063-023-11296-z · Cited by 15
“[14]designedATAE-LSTMthatconcatenatestargetandwordrepresentationstocomputeattentionweights.”
BackgroundMethodSentiment information extraction of comparative sentences based on CRF model
Wang, W., Xin, G., Wang, B., Huang, J., & Liu, Y. (2017) · Computer Science and Information Systems · doi:10.2298/csis161229031w · Cited by 16
“Representation learning has been successfully applied to natural language processing, such as information extraction, sentiment analysis [19,16,2] and so on.”
MethodChinese metaphor sentiment computing via considering culture
Su, C., Li, J., Ying, P., & Chen, Y. (2019) · Neurocomputing · doi:10.1016/j.neucom.2019.03.087 · Cited by 16
DA-BERT: Enhancing Part-of-Speech Tagging of Aspect Sentiment Analysis Using BERT
Pei, S., Wang, L., Shen, T., & Ning, Z. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-29611-7_7 · Cited by 14
Toward Tag-free Aspect Based Sentiment Analysis: A Multiple Attention Network Approach
Qiang, Y., Li, X., & Zhu, D. (2020) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn48605.2020.9207426 · Cited by 16
“AT-LSTM [28] adds an attention layer following the LSTM layer aiming to capture the vital words in response to the whole review sentences for better sentiment polarities classification.”
BackgroundMethodMeasuring and Improving Faithfulness of Attention in Neural Machine Translation
Moradi, P., Kambhatla, N., & Sarkar, A. (2021) · Conference of the European Chapter of the Association for Computational Linguistics · doi:10.18653/v1/2021.eacl-main.243 · Cited by 22
“These weights are often implicitly or explicitly regarded as an interpretation for the model’s prediction at the time step t (Tu et al., 2016; Mi et al., 2016; Liu et al., 2016; Wang et al., 2016; Lee et al., 2017; Ding et al., 2017; Ghaeini et al., 2018).”
BackgroundJointly Modeling Aspect and Polarity for Aspect-based Sentiment Analysis in Persian ReviewsPreprint
Vazan, M., & Razmara, J. (2021) · arXiv (Cornell University) · doi:10.13140/rg.2.2.12339.14887/1 · Cited by 16
A Knowledge-Enhanced and Topic-Guided Domain Adaptation Model for Aspect-Based Sentiment Analysis
Zeng, Y., Wang, G., Ren, H., Cai, Y., Leung, H.-F., Li, Q., & Huang, Q. (2023) · IEEE Transactions on Affective Computing · doi:10.1109/taffc.2023.3292213 · Cited by 13
“More specifically, aspect extraction [15], [16], [17], [18], [19], [20], [21] and aspect sentiment classification [22], [23], [24], [25], [26], [27] have been well studied in the literature.”
BackgroundZheng, Y., & Li, X. (2024) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v38i17.29945 · Cited by 13
“…in multiple ways: 1) Modeling position information using attention mechanisms, where the core idea is that contexts close to the aspect receive greater attention (Wang et al. 2016; Fan, Feng, and Zhao 2018; Huang, Ou, and Carley 2018; Gu et al. 2018; Li, Liu, and Zhou 2018; Phan and Ogunbona 2020).”
BackgroundWeng, Y., Chen, L., Wang, S., Ye, X., Liu, X., Liu, Z., & Chaomurilige, C. (2024) · Heliyon · doi:10.1016/j.heliyon.2024.e32967 · Cited by 15
Prompt Fusion Interaction Transformer For Aspect-Based Multimodal Sentiment Analysis
Yang, D., Li, X., Li, Z., Zhou, C., Wang, X., & Chen, F. (2024) · IEEE International Conference on Multimedia and Expo (ICME) · doi:10.1109/icme57554.2024.10687885 · Cited by 13
Polarity-aware deep attention network for aspect-based sentiment analysis
Wadawadagi, R. S., Tiwari, S., & Pagi, V. B. (2024) · Progress in Artificial Intelligence · doi:10.1007/s13748-024-00352-x · Cited by 13
Ding, Y., Lei, Y., Wang, A., Liu, X., Zhu, T., & Li, Y. (2024) · Neurocomputing · doi:10.1016/j.neucom.2024.128849 · Cited by 16
Span-based syntactic feature fusion for aspect sentiment triplet extraction
Xu, G., Yang, Z., Xu, B., Luo, L., & Lin, H. (2025) · Information Fusion · doi:10.1016/j.inffus.2025.103078 · Cited by 13
Semantic enhanced bi-syntactic graph convolutional network for aspect-based sentiment analysis
Xiao, J., Xue, Y., & Li, F. (2025) · Information Sciences · doi:10.1016/j.ins.2025.122130 · Cited by 13
A survey on aspect sentiment triplet extraction methods and challenges
Zou, W., Sun, X., Zhao, X., Feng, J. H., Long, Y., & Xing, Y. (2025) · Computer Science Review · doi:10.1016/j.cosrev.2025.100761 · Cited by 14
Improving Sentiment Classification in Slovak Language
Pecar, S., Šimko, M., & Bieliková, M. (2019) · Workshop on Balto-Slavic Natural Language Processing (BSNLP) · doi:10.18653/v1/w19-3716 · Cited by 13
“Whereas state-of-the-art methods widely employ different neural model architectures, such as the attention mechanism (Wang et al., 2016) or model ensemble techniques (Araque et al., 2017), recent research in sentiment analysis in Slavic languages still employs more traditional machine learning…”
MethodXRA-Net Framework for Visual Sentiments Analysis
Yadav, A., Agarwal, A., & Vishwakarma, D. K. (2019) · IEEE International Conference on Multimedia Big Data · doi:10.1109/bigmm.2019.00-22 · Cited by 15
“[21] applied LSTM with attention for aspect-based sentiment analysis so that the model could concentrate on various parts of the sentence.”
MethodExploring Disorder-Aware Attention for Clinical Event Extraction
Yadav, S., Ramteke, P., Ekbal, A., Saha, S., & Bhattacharyya, P. (2020) · ACM Transactions on Multimedia Computing Communications and Applications · doi:10.1145/3372328 · Cited by 13
Fast Sentiment Analysis Algorithm Based on Double Model Fusion
Lin, Z., Wang, L., Cui, X., & Gu, Y. (2020) · Computer Systems Science and Engineering · doi:10.32604/csse.2021.014260 · Cited by 13
“[4] proposed a topic-specific sentiment analysis method based on the LSTM with attention mechanism, which focused on the characteristics of different parts of the sentence through the attention mechanism, and achieved good performance on the task of sentiment classification of specific topics.”
MethodDNN-driven Gradual Machine Learning for Aspect-term Sentiment Analysis
Ahmed, M., Chen, Q., Wang, Y., Nafa, Y., Li, Z., & Duan, T. (2021) · Findings of the Association for Computational Linguistics: ACL (Findings of ACL) · doi:10.18653/v1/2021.findings-acl.43 · Cited by 19
“In comparison, the DNN-based models equipped with an attention mechanism have been shown to be more effective on ATSA (Tang et al., 2016b; Wang et al., 2016; Tang et al., 2016a).”
BackgroundMethodSelf-citationPathan, A. F., & Prakash, C. (2021) · Journal of King Saud University - Computer and Information Sciences · doi:10.1016/j.jksuci.2021.09.011 · Cited by 19
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.