The DOI matches its Crossref record; 40 of the 40 references it cites were found in a registry or an index.
Bi-LSTM Model to Increase Accuracy in Text Classification: Combining Word2vec CNN and Attention Mechanism
Open accessAbstract
There is a need to extract meaningful information from big data, classify it into different categories, and predict end-user behavior or emotions. Large amounts of data are generated from various sources such as social media and websites. Text classification is a representative research topic in the field of natural-language processing that categorizes unstructured text data into meaningful categorical classes. The long short-term memory (LSTM) model and the convolutional neural network for sentence classification produce accurate results and have been recently used in various natural-language processing (NLP) tasks. Convolutional neural network (CNN) models use convolutional layers and maximum pooling or max-overtime pooling layers to extract higher-level features, while LSTM models can capture long-term dependencies between word sequences hence are better used for text classification. However, even with the hybrid approach that leverages the powers of these two deep-learning models, the number of features to remember for classification remains huge, hence hindering the training process. In this study, we propose an attention-based Bi-LSTM+CNN hybrid model that capitalize on the advantages of LSTM and CNN with an additional attention mechanism. We trained the model using the Internet Movie Database (IMDB) movie review data to evaluate the performance of the proposed model, and the test results showed that the proposed hybrid attention Bi-LSTM+CNN model produces more accurate classification results, as well as higher recall and F1 scores, than individual multi-layer perceptron (MLP), CNN or LSTM models as well as the hybrid models.
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
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 source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“On the other hand, long-term dependencies between word sequences can be captured by LSTM models, which is a vital requirement in the context of cyberbullying detection [125].”
From A Review on Deep-Learning-Based Cyberbullying Detection (2023) · cites this paper as [125]
Experimental — accuracy not yet measured
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
BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding
Devlin, J., Chang, M.-W., Lee, K., & Toutanova, K. (2018) · arXiv · doi:10.48550/arxiv.1810.04805 · Cited by 73,173 · cited 1×
“The model leverages the novelty of BERT (bidirectional encoder representation from transformers) [31] for text extraction.”
MethodConvolutional 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×
“To further increase the sentiment classification accuracy of unstructured text, Yoon Kim [7] proposed a 1D CNN approach for text classification.”
MethodFramewise phoneme classification with bidirectional LSTM and other neural network architectures
Graves, A., & Schmidhuber, J. (2005) · Neural Networks · doi:10.1016/j.neunet.2005.06.042 · Cited by 6,152
Bag of Tricks for Efficient Text Classification
Joulin, A., Grave, E., Bojanowski, P., & Mikolov, T. (2017) · Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics: Volume 2, Short Papers · doi:10.18653/v1/e17-2068 · Cited by 4,545
A 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×
“With the 1D CNN, the convolution layer uses a 1D cross-correlation operation that involves a sliding convolution window with variable-size kernels over the input text starting from left to right [13].”
MethodRecurrent Convolutional Neural Networks for Text Classification
Lai, S., Xu, L., Liu, K., & Zhao, J. (2015) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v29i1.9513 · Cited by 2,384
Deep learning for sentiment analysis: A survey
Zhang, L., Wang, S., & Liu, B. (2018) · Wiley Interdisciplinary Reviews Data Mining and Knowledge Discovery · doi:10.1002/widm.1253 · Cited by 2,182 · cited 1×
“Natural-language-based sentiment classification has a wide range of applications, such as movie review classification, subjective and objective sentence classification, and text classification technology [1].”
BackgroundComparative Study of CNN and RNN for Natural Language ProcessingPreprint
Yin, W., Kann, K., Yu, M., & Schütze, H. (2017) · arXiv (Cornell University) · doi:10.48550/arxiv.1702.01923 · Cited by 1,264 · cited 1×
“Figure 2 shows the basic architecture of the 1D CNN [14].”
BackgroundBidirectional LSTM with attention mechanism and convolutional layer for text classification
Liu, G., & Guo, J. (2019) · Neurocomputing · doi:10.1016/j.neucom.2019.01.078 · Cited by 1,166 · cited 1×
“1D CNN processes text as a one-dimensional image and a 1D CNN is used to capture the latent associations between neighboring words, in contrast with LSTMs, which process each word in a sequential pattern [8].”
MethodA Convolutional Neural Network for Modelling SentencesPreprint
Kalchbrenner, N., Grefenstette, E., & Blunsom, P. (2014) · arXiv (Cornell University) · doi:10.48550/arxiv.1404.2188 · Cited by 967 · cited 1×
“With the 1D CNN, the convolution layer uses a 1D cross-correlation operation that involves a sliding convolution window with variable-size kernels over the input text starting from left to right [13].”
Method
Research works printed but not linked: 2
- Pouyanfar, 2018, A survey on deep learning: Algorithms, techniques, and applications, ACM Comput. Surv. (CSUR), 51, 1
- Huang, Z., Xu, W., and Yu, K. (2015). Bidirectional LSTM-CRF models for sequence tagging. arXiv.
Cited by
Sorted by citations
Items 401–442 of 442
Political HateCheck: Fine-tuning Offensive Tweets for Hate Speech Detection
Gautam, M., & Mahalakshmi, R. (2025) · Lecture notes in networks and systems · doi:10.1007/978-3-032-03527-1_12
Deep Learning for Precision Agriculture: Predicting Crop Yields in a Changing Climate
Choubey, M., Gupta, Y. K., Dubey, A., & Prasad, R. (2025) · Springer eBooks · doi:10.1007/978-981-95-1268-3_14
Murugiah, P. (2025) · Wireless Networks · doi:10.1007/s11276-025-04034-x
Raj, S., & Singh, S. K. (2025) · Arabian Journal of Geosciences · doi:10.1007/s12517-025-12376-1
“This bidirectional processing enables the model to have a more comprehensive view of the entire sequence, making it particularly powerful in tasks where understanding both past and future context is critical (Jang et al. 2020). incorporates human-perceived weather effects, enriching the analysis.”
GRAPHSUMFORMER: A Hybrid Transformer-GNN Model for Enhanced Abstractive Text Summarization
Deepa, R., Sharmila, T. S., & Niruban, R. (2025) · International Conference on Recent Innovation in Science Engineering and Technology (ICRISET) · doi:10.1109/icriset64803.2025.11252495
“[4 ] Traditional text summarization methods primarily focus on extractive summarization [5].”
Raveendran, N., Arya, A., Sanjana, D., Ranjini, R. S., Haritha, M., & Hegde, V. (2025) · IEEE International Conference on Contemporary Computing and Communications (InC4) · doi:10.1109/inc465408.2025.11256297
“While the model performed well overall, some test samples were misclassified . c) CNN-LSTM with Word2Vec: We used Word2Vec for word embedding and CNN-LSTM [16] for classification.”
Hasan, M. R., Chong, Z., Abdulwasea, T. K., Rashid, H. O., & Sultana, F. (2025) · International Symposium on Multidisciplinary Studies and Innovative Technologies (ISMSIT) · doi:10.1109/ismsit67332.2025.11268079
Ding, Y., Shalaby, M., Singh, N. S. S., & Alfilh, R. H. C. (2025) · Scientific Reports · doi:10.1038/s41598-025-31954-7 · Cited by 1
“Similarly, Jang et al. 25 developed attention-guided Bi-LSTM+CNN architectures that synergistically exploit both sequential and spatial textual features 26 .”
Defect text recognition and condition assessment method of power equipment based on BERT-BiLSTM
Shao, J., Li, X., Liu, T., Chen, H., Wang, T., & Wei, C. (2025) · PeerJ Computer Science · doi:10.7717/peerj-cs.3318
Additional file 1 of A conversational agent system for dietary supplements use
Singh, E., Bompelli, A., Wan, R., Bian, J., Pakhomov, S., & Zhang, R. (2022) · Figshare · doi:10.6084/m9.figshare.20267484
An Analysis of Cross-Lingual Natural Language Processing for Low-Resource Languages
Naik, V., Rajeswari, K., Jadhav, K., & Rahalkar, A. (2025) · Lecture notes in networks and systems · doi:10.1007/978-981-96-6438-2_4
Occupant-Based Digital Predictive Management to Improve the Built Environment
D’Orazio, M., Gulli, R., Salvalai, G., Massafra, A., Bernardini, G., Villa, R. V. R., Grecchi, M., Predari, G., & Romano, G. (2025) · Lecture notes in civil engineering · doi:10.1007/978-3-032-06993-1_16
Accelerating DNA Sequence Alignment Using Optimized AI Techniques
Supriya, K., Kumar, R. K., & Lalitha, S. (2025) · Lecture notes in electrical engineering · doi:10.1007/978-981-96-9971-1_5
Türkçe Haber Metinlerinin Derin Öğrenme Modelleriyle Sınıflandırılması: Karşılaştırmalı Bir İnceleme
Suna, N. D., & Kaynar, O. (2025) · Bilgisayar bilimleri ve mühendisliği dergisi. · doi:10.54525/bbmd.1708770
Ayon, Z. A. H., Abdullah, M. Z. T., Ismail, N. H., Kamarudin, N. S., & Murti, M. A. (2025) · International Conference on Software Engineering and Computer Systems · doi:10.1109/icsecs65227.2025.11279065
“LSTMs are effective for processing complex textual data by maintaining contextual information over long sequences, addressing the vanishing gradient problem found in standard RNNs [24], [25].”
Yu, H., Han, Y., Xu, L., Wei, T., & Zhang, X. (2026) · Regional Studies in Marine Science · doi:10.1016/j.rsma.2026.104785
Fadiannur, H., & Sibaroni, Y. (2025) · International Conference on Intelligent Cybernetics Technology & Applications (ICICyTA) · doi:10.1109/icicyta68677.2025.11362370
“Performance is evaluated using the metrics accuracy, recall, precision, and f1-score, which can be seen in Equations (10) - (13) [12].”
Implementation of GRU Model for Identifying Hoax News in Indonesia: A Focus on Cyber Security
Wibowo, C. I., & Yakub, S. Y. (2025) · IEEE International Conference on Cryptography, Informatics, and Cybersecurity (ICoCICs) · doi:10.1109/icocics68032.2025.11384007
“Several studies have combined LSTM or GRU with attention and shown significant improvements in F1-score and AUC, especially on long and unstructured text data [26], [27].”
An Efficient GRU Based Approach for Next Word Prediction
Gupta, R., & Rawat, R. (2025) · International Conference on Intelligent Computing, Information and Control Systems (ICOIICS) · doi:10.1109/icoiics67115.2025.11390413
“[4] Gated Recurrent Unit is a improved version of standard RNN implementing a update and reset gate which helps in deciding which information should be passed to the output.”
Indonesian Named Entity Recognition (NER) Using IndoBERT, BiLSTM, and CRF Models
Abdurrahman, G., Warisaji, T. T., Nilogiri, A., Wardoyo, A. E., Bakti, B. S., Umilasari, R., Amiri, Y. I. A., Wardati, N. K., & Arifin, Z. (2025) · Beyond Technology Summit on Informatics International Conference (BTS-I2C) · doi:10.1109/bts-i2c67944.2025.11399304
“[8], while CRF plays a role in optimizing label prediction by calculating transitions between labels globally.”
Vaishnav, N. K., & Karmakar, S. (2026) · International Journal of Scientific Research in Computer Science Engineering and Information Technology · doi:10.32628/cseit2612130
Forecasting UFO Sightings via Deep Learning and Natural Language Generation
Costa, L. F. P., & Kaur, K. (2025) · IEEE International Conference on Future Machine Learning and Data Science (FMLDS) · doi:10.1109/fmlds67896.2025.00071
“Due to limitations in resource-constrained environments, external language models such as Google’s Gemini API were utilized to enhance grammaticality and contextual fidelity of generated outputs [4], [5].”
Orvalamarva, O., Pratiwi, O. N., & Fakhrurroja, H. (2026) · International Journal of Advances in Data and Information Systems · doi:10.59395/ijadis.v7i1.1492
“This performance difference suggests that for datasets comprising relatively short questions, local features ( n-grams ) extracted by CNN such as detecting specific operational verbs (e.g., “explain,” “mention”) are more effective than BiLSTM's long-term sequence modeling [28].”
Saputra, S. L., & Mauritsius, T. (2026) · International Seminar on Intelligent Business and Edge-Computing Research (ISIBER) · doi:10.1109/isiber68248.2026.11469922
“Empirical studies show that Bi-LSTM can effectively capture long-term dependencies between word sequences, leading to improved text classification performance and higher F1-scores compared to other models such as CNN or MLP [20].”
Spam-Fighting Network: An AI-Based System for Large-Scale Spam Detection in Telecom Networks
Tunuguntla, S. T., Chauhan, K., Chakraborty, B., Mathur, A., & Singh, A. (2025) · Joint International Conference on Data Science & Management of Data (CODS-COMAD) · doi:10.1145/3799830.3799883
Exploring Regional Variation in Bangla: Automating Dialect Classification Using Deep Learning
Badhan, M. H., Ahmod, R., Purkayastha, P., Talukder, S. D., Mahin, M. R., & Mojumder, M. A. N. (2025) · International Conference on Computer and Information Technology (ICCIT) · doi:10.1109/iccit68739.2025.11490135
“Among the available approaches, BiLSTM models enhanced with attention mechanisms have proven highly efficient at understanding information from both earlier and later parts of a context and focusing on informative segments of the input [6] [7].”
Hybrid attention-based multi-class classification of Ethiopian legal texts using deep learning
Alemu, A. A., Melese, M. D., Mengesha, D. A., & Widneh, M. A. (2026) · PLoS ONE · doi:10.1371/journal.pone.0348805
Alsaad, M. M. B., & Joshi, H. (2026) · AIP conference proceedings · doi:10.1063/5.0330719
Adaptive and multi-scale feature fusion for Chinese news headline classification
Yan, Y. (2026) · PLoS ONE · doi:10.1371/journal.pone.0345779
“Neural network models such as Recurrent Neural Networks (RNN) [20], Convolutional Neural Networks (CNN) [21], Long Short-Term Memory networks (LSTM) [22], and FastText [23] have been widely adopted.”
Explainable Multimodal LLMs for Intelligent Human–Machine Interaction
Hebbar, K. S. (2026) · International Conference Big Data and Machine Learning · doi:10.1109/icbdml68582.2026.11544179
Overview and Bibliometric Analysis of Text Mining in Transportation Field
Jia, R., Xu, X., Xiao, D., & Du, B. (2026) · Lecture notes in electrical engineering · doi:10.1007/978-981-95-8620-2_1
(2026) · Elsevier eBooks · doi:10.1016/b978-0-443-51094-6.00005-0
Altabey, W. A. (2026) · Sound&Vibration · doi:10.59400/sv4028
“Speaking of that, we’ve categorized structural damage detection as a sequence classification problem in this study [ 40].”
Layer Wise IndoBERT Representation Evolution for Indonesian Misinformation DetectionPreprint
Anggrainingsih, R., Dewanto, J., & Hassan, G. M. (2026) · Research Square · doi:10.21203/rs.3.rs-9940304/v1
AbouGrad, H., & Shabarshov, A. (2026) · Advances in Science, Technology & Innovation/Advances in science, technology & innovation · doi:10.1007/978-3-032-14373-0_15
Sentana, I. W. B., Rangganata, M. I., Wardana, I. N. K., Saptarini, N. G. A. P. H., Suwirmayanti, N. L. G. P., & Diaz, R. A. N. (2026) · International Conference on Intelligent and Sustainable AI Systems (ICOSAAS) · doi:10.1109/icosaas68663.2026.11648483
“Recent advancements have pushed toward hybrid multimodal data-fusion paradigms — extracting semantic text features via Optical Character Recognition (OCR) and pairing them with visual features using Bi-LSTM, ResNet, BERT, or CLIP backends [12], [13].”
Zhang, X. (2026) · International Journal of Pattern Recognition and Artificial Intelligence · doi:10.1142/s0218001426400331
Sun, P., Zhang, F., Qiu, Z., Chang, J., Zhang, H., & Li, G. (2026) · Energy Conversion and Economics · doi:10.1049/enc2.70048
An Interpretable Hybrid Ensemble Model for Paraphrase Detection With SHAP-Based Explanations
Sameh, D., El-Sawy, A., Amer, E., & Nayel, H. (2026) · IEEE Access · doi:10.1109/access.2026.3729013
“On semantic textual similarity and paraphrasing benchmarks, such as the Quora Question Pairs dataset (QQP), pretrained models like BERT, RoBERTa, and Sentence-BERT have demonstrated impressive performance [12], [13].”
Bi-LSTM & LeNet model for insurance policy summarization and classification
Kolambe, S., & Kaur, P. (2026) · Discover Artificial Intelligence · doi:10.1007/s44163-026-02139-6
“Bi-LSTM: Bi-LSTM [32], a variant of RNN, is designed to address the limitations of unidirectional sequential learning.”
Espino, C. A., Bernades, M. P., Orcena, R. L., Nacion, P. R. P., Bucao, W. F., & Balangue, O. V. (2026) · International Conference on Advanced Machine Learning and Data Science (AMLDS) · doi:10.1109/amlds69611.2026.11724236
Yang, P., Qin, Y., & Luo, Y. (2026) · Concurrency and Computation Practice and Experience · doi:10.1002/cpe.71010
Metadata
- Authors
- Jang, B., Kim, M., Harerimana, G., Kang, S.-U., & Kim, J. W.
- Affiliations
- Sangmyung University (KR)
- Corresponding author
- Kim, Jong Wook
- Venue
- Applied Sciences
- Publisher
- MDPI AG
- Published
- 2020-08-24
- Volume
- 10
- Issue
- 17
- Pages
- 5841
- ISSN
- 2076-3417 (ISSN-L)
- OpenAlex
- W3080359515
- Cited by
- 442
- References
- 33
- Citations by year
- 2026: 25 · 2025: 93 · 2024: 97 · 2023: 101 · 2022: 73 · 2021: 50 · 2020: 3
- FWCI
- 22.27
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- Applied Sciences (publishedVersion, cc-by)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Funders
- National Research Foundation of Korea (NRF-2019R1F1A1058058)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Topic Modeling
- Physical Sciences › Computer Science › Artificial Intelligence › Sentiment Analysis and Opinion Mining
- Physical Sciences › Computer Science › Artificial Intelligence › Text and Document Classification Technologies
- Keywords
- text classification, bidirectional LSTM, convolutional neural networks, attention mechanism, Word2Vec, IMDB movie reviews, sentiment analysis, feature extraction, long short-term memory
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
