A Robust Sentiment Analysis Method Based on Sequential Combination of Convolutional and Recursive Neural Networks
The DOI matches its Crossref record; 43 of the 43 references it cites were found in a registry or an index.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
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?
In the citing paper
“RvNN has been employed in several applications [60–62].”
From Review of deep learning: concepts, CNN architectures, challenges, applications, future directions (2021) · cites this paper as [61]
Citations
Cites
Distributed 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 · cited 3×
“In this regard, Word2Vec model which is a shallow two layers neural network introduced by Mikolov [23] is used in the first layer of the proposed model.”
BackgroundMethodInfluentialConvolutional Neural Networks for Sentence Classification
Kim, Y. (2014) · Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP) · doi:10.3115/v1/d14-1181 · Cited by 14,831 · cited 2×
“Following a similar line of research, a series of experiments were carried out by Kim [25] who used one layer CNN on top of pre-trained vectors extracted from Word2Vec model for sentence classification and especially sentiment analysis.”
BackgroundMethodLearning Word Vectors for Sentiment Analysis
Maas, A. L., Daly, R. E., Pham, P. T., Huang, D., Ng, A. Y., & Potts, C. (2011) · Cited by 6,960
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 4×
“Stanford Sentiment Treebank (SST) dataset [29] was used for evaluation in this paper due to its ability for training and evaluating compositional models.”
BackgroundMethodResultInfluentialNatural Language Processing (almost) from Scratch
Collobert, R., Weston, J., Bottou, L., Karlen, M., Kavukcuoglu, K., & Kuksa, P. P. (2011) · arXiv (Cornell University) · doi:10.48550/arxiv.1103.0398 · Cited by 4,962 · cited 1×
“According to Collobert et al. [37], sentence matrix can be treated as an image and convolutional operation can be performed using linear filters.”
MethodDistributed Representations of Sentences and Documents
Le, Q. V., & Mikolov, T. (2014) · arXiv (Cornell University) · doi:10.48550/arxiv.1405.4053 · Cited by 4,934 · cited 1×
“To solve this issue, advanced representations called word embedding have been proposed that employ high dimensional space to encode word similarity as distance [21].”
BackgroundA Convolutional Neural Network for Modelling Sentences
Kalchbrenner, N., Grefenstette, E., & Blunsom, P. (2014) · Proceedings of the 52nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.3115/v1/p14-1062 · Cited by 3,601 · cited 1×
“The convolutional layer aims to extract local features while retaining the sequential information of the sentence context [25, 36].”
BackgroundSentiment analysis algorithms and applications: A survey
Medhat, W., Hassan, A., & Korashy, H. (2014) · Ain Shams Engineering Journal · doi:10.1016/j.asej.2014.04.011 · Cited by 3,248 · cited 1×
“On the other hand, machine learning techniques contain some models such as Naïve Base (NB), Maximum Entropy (ME) and Support Vector Machine (SVM) that have achieved considerable success in the field of sentence classification and sentiment analysis [9–11].”
MethodImproved Semantic Representations From Tree-Structured Long Short-Term Memory Networks
Tai, K. S., Socher, R., & Manning, C. D. (2015) · Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing (Volume 1: Long Papers) · doi:10.3115/v1/p15-1150 · Cited by 3,081 · cited 1×
“[42] Bi-LSTM [42] Tree-LSTM [42] Tree-GRU [43] Tree-GRU+attention [43] LSTM+RNN+attention [44] 46.”
Recent Trends in Deep Learning Based Natural Language Processing [Review Article]
Young, T., Hazarika, D., Poria, S., & Cambria, E. (2018) · IEEE Computational Intelligence Magazine · doi:10.1109/mci.2018.2840738 · Cited by 2,921
Attention-based LSTM for Aspect-level Sentiment Classification
Wang, Y., Huang, M., zhu, X., & Zhao, L. (2016) · Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing · doi:10.18653/v1/d16-1058 · Cited by 2,450
A survey on opinion mining and sentiment analysis: Tasks, approaches and applications
Ravi, K., & Ravi, V. (2015) · Knowledge-Based Systems · doi:10.1016/j.knosys.2015.06.015 · Cited by 1,306
(2011) · Cited by 1,192
Recent Trends in Deep Learning Based Natural Language Processing
Young, T., Hazarika, D., Poria, S., & Cambria, E. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1708.02709 · Cited by 1,192 · cited 3×
“Additionally, whereas these methods have poor mathematical theories, adjusting their hyperparameters for training is difficult and regularization must be done by trial and error [12, 34, 35].”
BackgroundInfluentialDeep Learning-Based Document Modeling for Personality Detection from Text
Majumder, N., Poria, S., Gelbukh, A., & Cambria, E. (2017) · IEEE Intelligent Systems · doi:10.1109/mis.2017.23 · Cited by 675
Combination of Convolutional and Recurrent Neural Network for Sentiment Analysis of Short Texts
Wang, X., Jiang, W., & Luo, Z. (2016) · International Conference on Computational Linguistics · Cited by 452
Sentiment Analysis Is a Big Suitcase
Cambria, E., Poria, S., Gelbukh, A., & Thelwall, M. (2017) · IEEE Intelligent Systems · doi:10.1109/mis.2017.4531228 · Cited by 439 · cited 1×
“In other words, the belief and perception of each person as well as the decisions who makes in life depend on the others’ viewpoint and assessment from the real world [1].”
BackgroundSentiment Analysis Using Deep Learning Techniques: A Review
Tul, Q., Ali, M., Riaz, A., Noureen, A., Kamranz, M., Hayat, B., & Rehman, A. (2017) · International Journal of Advanced Computer Science and Applications · doi:10.14569/ijacsa.2017.080657 · Cited by 334
Sentiment Analysis Using Convolutional Neural Network
Ouyang, X., Zhou, P., Li, C. H., & Liu, L. (2015) · 2015 IEEE International Conference on Computer and Information Technology; Ubiquitous Computing and Communications; Dependable, Autonomic and Secure Computing; Pervasive Intelligence and Computing · doi:10.1109/cit/iucc/dasc/picom.2015.349 · Cited by 239 · cited 3×
“Ouyang et al. [14] also proposed a seven layers framework that employed Word2Vec for representation.”
BackgroundMethodTracking Control of Robot Manipulators with Unknown Models: A Jacobian-Matrix-Adaption Method
Chen, D., Zhang, Y., & Li, S. (2017) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2017.2766455 · Cited by 227
RNN Models for Dynamic Matrix Inversion: A Control-Theoretical Perspective
Jin, L., Li, S., & Hu, B. (2018) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2017.2717079 · Cited by 209
Analysis on the Dropout Effect in Convolutional Neural Networks
Park, S., & Kwak, N. (2017) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-54184-6_12 · Cited by 194 · cited 1×
“Dropout is a regularization method which prevents the network from overfitting by randomly ignoring a number of samples in each training iteration [39].”
MethodJin, L., Li, S., Hu, B., Liu, M., & Yu, J. (2019) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2018.2798642 · Cited by 179 · cited 1×
“Although the use of deep learning has led to significant improvements over previous approaches in the field of sentiment analysis, these models are still confronted with some limitations [5, 33].”
BackgroundDeep Learning approach for sentiment analysis of short texts
Hassan, A., & Mahmood, A. (2017) · 2017 3rd International Conference on Control, Automation and Robotics (ICCAR) · doi:10.1109/iccar.2017.7942788 · Cited by 168 · cited 4×
“Combinational models CNN-GRU [30] CNN-LSTM [30] ConvLstm [15] Recursive-recurrent [32] RCNN [40] 2-channel CNN-Tree-LSTM [16] CNN-LSTM (Glove Amazon) [16] 50 • By comparing the proposed model with traditional convolutional and recursive neural networks, it can be concluded that the proposed model…”
BackgroundMethodInfluentialMultichannel Variable-Size Convolution for Sentence Classification
Yin, W., & Schütze, H. (2015) · Proceedings of the Nineteenth Conference on Computational Natural Language Learning · doi:10.18653/v1/k15-1021 · Cited by 162 · cited 1×
“B Convolutional based networks CNN-1 layer [36] CNN-non static [25] CNN-multichannel [25] DCNN [36] MVCNN [41] 37.”
Chen, D., & Zhang, Y. (2017) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2017.2764529 · Cited by 149 · cited 2×
“On the other hand, tree-based models are less affected by outliers and can consider syntactic relations and therefore using a recursive neural network can increase the robustness of the proposed model due to its tree structure [17–20].”
BackgroundMethodEnhanced news sentiment analysis using deep learning methods
Souma, W., Vodenska, I., & Aoyama, H. (2019) · Journal of Computational Social Science · doi:10.1007/s42001-019-00035-x · Cited by 146
You, Q., Cao, L., Jin, H., & Luo, J. (2016) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/2964284.2964288 · Cited by 129 · cited 2×
“On the other hand, tree-based models are less affected by outliers and can consider syntactic relations and therefore using a recursive neural network can increase the robustness of the proposed model due to its tree structure [17–20].”
MethodA survey on sentiment analysis methods and approach
Abirami, A. M., & Gayathri, V. (2017) · International Conference on Advanced Computing · doi:10.1109/icoac.2017.7951748 · Cited by 121 · cited 1×
“Sentiment analysis techniques are generally categorized into two distinct groups [8]: lexicon based and machine learning based techniques.”
MethodChallenges in Sentiment Analysis
Mohammad, S. M. (2017) · Socio-affective computing · doi:10.1007/978-3-319-55394-8_4 · Cited by 114 · cited 1×
“Although deep learning based networks have accomplished higher performance in the task of sentiment analysis, they are still confronted with some limitations [13].”
BackgroundVisual Sentiment Analysis for Social Images Using Transfer Learning Approach
Islam, J., & Zhang, Y. (2016) · doi:10.1109/bdcloud-socialcom-sustaincom.2016.29 · Cited by 103 · cited 1×
“Based on this point, Isalm and Zhang [24] presented a novel CNN framework that has been implemented using Caffee and Python on Linux machine.”
MethodDeep Sentiment Representation Based on CNN and LSTM
Huang, Q., Chen, R., Zheng, X., & Dong, Z. (2017) · International Conference on Green Informatics (ICGI) · doi:10.1109/icgi.2017.45 · Cited by 92 · cited 1×
“A similar model was proposed by Huang et al. [31] that employed pre-trained word vectors as input and CNN to extract local features.”
MethodStructural Attention Neural Networks for improved sentiment analysis
Kokkinos, F., & Potamianos, A. (2017) · Conference of the European Chapter of the Association for Computational Linguistics · doi:10.18653/v1/e17-2093 · Cited by 78
Chen, D., Li, S., & Wu, Q. (2018) · Sensors · doi:10.3390/s19010074 · Cited by 56
Robustness analysis of a hybrid of recursive neural dynamics for online matrix inversion
Chen, K., & Yi, C. (2015) · Applied Mathematics and Computation · doi:10.1016/j.amc.2015.10.026 · Cited by 48
Approaches to Sentiment Analysis on Product Reviews
Vyas, V., & Uma, V. (2018) · Advances in business information systems and analytics book series · doi:10.4018/978-1-5225-4999-4.ch002 · Cited by 41 · cited 1×
“Therefore, opinion and all its related concepts such as feeling, judgments, and emotions are at the centers of research in the field of sentiment analysis [2].”
BackgroundRobustness of Deep Convolutional Neural Networks for Image Recognition
Uličný, M., Lundström, J., & Byttner, S. (2016) · Communications in computer and information science · doi:10.1007/978-3-319-30447-2_2 · Cited by 25 · cited 2×
“To overcome the problem of overfitting which decreases the robustness of a model, several methods have been proposed and dropout is the one that is efficiently used for this aim [20, 38].”
MethodCombining Convolution and Recursive Neural Networks for Sentiment Analysis
Van, V. D., Thai, T., & Nghiem, M.-Q. (2017) · International Symposium on Information and Communication Technology · doi:10.1145/3155133.3155158 · Cited by 25 · cited 5×
“Based on the evaluation method employed by Van et al. [16], all variations of the proposed model were evaluated using mean and standard deviation of the 5 runs.”
BackgroundMethodInfluentialImproving Weak Queries using Local Cluster Analysis as a Preliminary Framework
Jadidinejad, A. H., & Sadr, H. (2015) · Indian Journal of Science and Technology · doi:10.17485/ijst/2015/v8i15/46754 · Cited by 20
Self-citationMultichannel Variable-Size Convolution for Sentence ClassificationPreprint
Yin, W., & Schütze, H. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1603.04513 · Cited by 19 · cited 1×
“B Convolutional based networks CNN-1 layer [36] CNN-non static [25] CNN-multichannel [25] DCNN [36] MVCNN [41] 37.”
Sadr, H., & Solimandarabi, M. N. (2019) · Journal of advances in computer research · Cited by 8
Self-citationA Novel Approach for Computing Semantic Relatedness of Geographic Terms
Soleimandarabi, M. N., & Mirroshandel, S. A. (2015) · Indian Journal of Science and Technology · doi:10.17485/ijst/2015/v8i27/60811 · Cited by 6
Sentiment Classification Via Recurrent Convolutional Neural Networks
Du, C., & Huang, L. (2017) · DEStech Transactions on Computer Science and Engineering · doi:10.12783/dtcse/cii2017/17268 · Cited by 6 · cited 1×
“Combinational models CNN-GRU [30] CNN-LSTM [30] ConvLstm [15] Recursive-recurrent [32] RCNN [40] 2-channel CNN-Tree-LSTM [16] CNN-LSTM (Glove Amazon) [16] 50 • By comparing the proposed model with traditional convolutional and recursive neural networks, it can be concluded that the proposed model…”
Method
Research works printed but not linked: 3
- Soleimandarabi MN, Mirroshandel SA, Sadr H (2015) A Survey of semantic relatedness measures. Int J Comput Sci Network Solut 3(2):243–247
- Zhang X, Zhao J, LeCun Y (2015) Character-level convolutional networks for text classification. In: Advances in neural information processing systems, pp 649-657
- Socher R, Huval B, Manning CD, Ng AY (2012) Semantic compositionality through recursive matrix-vector spaces. In: Proceedings of the 2012 joint conference on empirical methods in natural language processing and computational natural language learning, association for computational linguistics, pp 1201–1211
Cited by
Review of deep learning: concepts, CNN architectures, challenges, applications, future directions
Alzubaidi, L., Zhang, J., Humaidi, A. J., Al-Dujaili, A., Duan, Y., Al-Shamma, O., Santamaría, J., Fadhel, M. A., Al-Amidie, M., & Farhan, L. (2021) · Journal of Big Data · doi:10.1186/s40537-021-00444-8 · Cited by 7,906
DCNNBiLSTM: An Efficient Hybrid Deep Learning-Based Intrusion Detection System
Hnamte, V., & Hussain, J. (2023) · Telematics and Informatics Reports · doi:10.1016/j.teler.2023.100053 · Cited by 259
Artificial Intelligence Image Recognition Method Based on Convolutional Neural Network Algorithm
Tian, Y. (2020) · IEEE Access · doi:10.1109/access.2020.3006097 · Cited by 245
“Sadr et al. [34] pointed out that the structure of the convolutional neural network itself is the main factor for the network to extract multi-level and multi-scale features.”
BackgroundOzkan-Okay, M., Akin, E., Aslan, Ö., Kosunalp, S., Iliev, T., Stoyanov, I., & Beloev, I. (2024) · IEEE Access · doi:10.1109/access.2024.3355547 · Cited by 236
“A recursive neural network (RvNN) applies the same set of weights repeatedly to a series of inputs to generate a fixed-width distributed representation [36], [78].”
MethodA Framework for Hate Speech Detection Using Deep Convolutional Neural Network
Roy, P. K., Tripathy, A. K., Das, T. K., & Gao, X.-Z. (2020) · IEEE Access · doi:10.1109/access.2020.3037073 · Cited by 205
Metadata
- Authors
- Sadr, H., Pedram, M. M., & Teshnehlab, M.
- Affiliations
- Islamic Azad University Rasht Branch (IR)
- Kharazmi University (IR)
- K. N. Toosi University of Technology (IR)
- Corresponding author
- Pedram, Mir Mohsen
- Venue
- Neural Processing Letters
- Published
- 2019-06-10
- Volume
- 50
- Issue
- 3
- Pages
- 2745-2761
- ISSN
- 1370-4621 (ISSN-L)
- 1573-773X
- OpenAlex
- W2952198026
- Cited by
- 82
- References
- 43
- Citations by year
- 2026: 3 · 2025: 5 · 2024: 11 · 2023: 18 · 2022: 15 · 2021: 17 · 2020: 13
- FWCI
- 5.19
- Type
- journal article
- Language
- en
- Open access
- closed
- Licence
- www.springer.com/tdm (tdm)
- www.springer.com/tdm (vor)
- Locations
- Neural Processing Letters (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Sentiment Analysis and Opinion Mining
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Physical Sciences › Computer Science › Artificial Intelligence › Hate Speech and Cyberbullying Detection
- Keywords
- sentiment analysis, convolutional neural networks, recurrent neural networks, hybrid CNN-RNN model, long-range dependencies, parameter efficiency, Stanford Sentiment Treebank
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.