Systematic Review of Deep Learning Models in Sentiment Analysis (2020-2025)
DOI:
https://doi.org/10.61856/s64z9e54Keywords:
Sentiment Analysis, Natural Language Processing, Deep Learning, Long Short-Term Memory, Bidirectional Long Short-Term MemoryAbstract
This review examines deep learning approaches to sentiment analysis published during 2020–2025, with an emphasis on recurrent and hybrid architectures. Twenty study entries are summarized by model architecture, dataset, application task, and reported performance. The selected evidence includes LSTM, BiLSTM, convolutional–recurrent models, and architectures incorporating BERT or RoBERTa. Reported results vary substantially across datasets and tasks, including sentiment polarity classification, emotion classification, aspect-based analysis, and recommendation applications. Because evaluation protocols and outcome measures differ, numerical scores are interpreted descriptively rather than pooled or used to establish universal model superiority. The synthesis identifies a need for clearer reporting of evaluation conditions and further assessment of domain transfer, linguistic variation, and model robustness.
References
K. Alahmadi, S. Alharbi, J. Chen, and X. Wang, “Generalizing sentiment analysis: a review of progress, challenges, and emerging directions,” Soc. Netw. Anal. Min., vol. 15, no. 1, p. 45, Apr. 2025, doi: 10.1007/s13278-025-01461-8.
Y. Bouassida and H. Mezali, “Enhancing Twitter Sentiment Analysis Using Hybrid Transformer and Sequence Models,” Japan Journal of Research, vol. 6, no. 1, article 089, 2025, doi: 10.33425/2690-8077.1163.
C. N. Dang, M. N. Moreno-García, and F. De La Prieta, “Hybrid Deep Learning Models for Sentiment Analysis,” Complexity, vol. 2021, no. 1, p. 9986920, Jan. 2021, doi: 10.1155/2021/9986920.
M. D. Devika, C. Sunitha, and A. Ganesh, “Sentiment Analysis: A Comparative Study on Different Approaches,” Procedia Computer Science, vol. 87, pp. 44–49, 2016, doi: 10.1016/j.procs.2016.05.124.
W. Etaiwi, D. Suleiman, and A. Awajan, “Deep Learning Based Techniques for Sentiment Analysis: A Survey,” Informatica, vol. 45, no. 7, Dec. 2021, doi: 10.31449/inf.v45i7.3674.
A. Glenn, P. LaCasse, and B. Cox, “Emotion classification of Indonesian Tweets using Bidirectional LSTM,” Neural Comput & Applic, vol. 35, no. 13, pp. 9567–9578, May 2023, doi: 10.1007/s00521-022-08186-1.
M. Greeshma and P. Simon, “Bidirectional Gated Recurrent Unit with Glove Embedding and Attention Mechanism for Movie Review Classification,” Procedia Computer Science, vol. 233, pp. 528–536, 2024, doi: 10.1016/j.procs.2024.03.242.
Y. Guo, Y. Liu, A. Oerlemans, S. Lao, S. Wu, and M. S. Lew, “Deep learning for visual understanding: A review,” Neurocomputing, vol. 187, pp. 27–48, 2016, doi: 10.1016/j.neucom.2015.09.116.
Mantasha Khan and Ankita Srivastava, “A Review on Sentiment Analysis of Twitter Data Using Machine Learning Techniques,” Feb. 2024, doi: 10.5281/ZENODO.10791471.
S. Li, K. Liu, and X. Chen, “A Context-Aware Personalized Recommendation Framework Integrating User Clustering and BERT-Based Sentiment Analysis,” Journal of Computer, Signal, and System Research, vol. 2, no. 6, pp. 100–108, 2025, doi: 10.71222/1cgq9333.
B. Liu, Sentiment Analysis and Opinion Mining. Morgan & Claypool Publishers, 2012, doi: 10.2200/S00416ED1V01Y201204HLT016.
J. Lu, H. Fan, and Y. Zhang, “Sentiment Analysis of IMDB Movie Reviews Based on LSTM,” J. adv. eng. technol., vol. 2, no. 2, June 2025, doi: 10.62177/jaet.v2i2.429.
U. B. Mahadevaswamy and P. Swathi, “Sentiment Analysis using Bidirectional LSTM Network,” Procedia Computer Science, vol. 218, pp. 45–56, 2023, doi: 10.1016/j.procs.2022.12.400.
D. Mahto, S. C. Yadav, and G. S. Lalotra, “Sentiment Prediction of Textual Data Using Hybrid ConvBidirectional-LSTM Model,” Mobile Information Systems, vol. 2022, pp. 1–11, June 2022, doi: 10.1155/2022/1068554.
Y. Mao, Q. Liu, and Y. Zhang, “Sentiment analysis methods, applications, and challenges: A systematic literature review,” Journal of King Saud University - Computer and Information Sciences, vol. 36, no. 4, p. 102048, Apr. 2024, doi: 10.1016/j.jksuci.2024.102048.
P. Mehta and D. S. Pandya, “A Review On Sentiment Analysis Methodologies, Practices And Applications,” vol. 9, no. 02, 2020.
G. S. N. Murthy, Shanmukha Rao Allu, Bhargavi Andhavarapu, Mounika Bagadi, Mounika Belusonti, “Text based Sentiment Analysis using LSTM,” IJERT, vol. V9, no. 05, p. IJERTV9IS050290, May 2020, doi: 10.17577/IJERTV9IS050290.
S. M. Orebi and A. M. Naser, “Opinion Mining in Text Short by Using Word Embedding and Deep Learning,” Journal of Applied Data Sciences, vol. 6, no. 1, pp. 526–636, 2025, doi: 10.47738/jads.v6i1.438.
I. Priyadarshini and C. Cotton, “A novel LSTM–CNN–grid search-based deep neural network for sentiment analysis,” J Supercomput, vol. 77, no. 12, pp. 13911–13932, Dec. 2021, doi: 10.1007/s11227-021-03838-w.
M. M. Rahman, A. I. Shiplu, Y. Watanobe, and M. A. Alam, “RoBERTa-BiLSTM: A Context-Aware Hybrid Model for Sentiment Analysis,” IEEE Trans. Emerg. Top. Comput. Intell., pp. 1–18, 2025, doi: 10.1109/TETCI.2025.3572150.
N. S and M. Kabadi, “A sentiment analysis framework using RoBERTa with Bi‐LSTM classification on Dynamic twitter data,” ETRI Journal, p. 10.4218/etrij.2024-0217, Aug. 2025, doi: 10.4218/etrij.2024-0217.
E. Sedqy Ibraihm Shlkamy, “A Russia-Ukraine Conflict Tweets Sentiment Analysis Using Bidirectional LSTM Network,” IJSR, vol. 12, no. 2, pp. 522–530, Feb. 2023, doi: 10.21275/SR23209172025.
A. C. M. V. Srinivas, Ch. Satyanarayana, Ch. Divakar, and K. P. Sirisha, “Sentiment Analysis using Neural Network and LSTM,” IOP Conf. Ser.: Mater. Sci. Eng., vol. 1074, no. 1, p. 012007, Feb. 2021, doi: 10.1088/1757-899X/1074/1/012007.
S. Taj, S. M. Daudpota, A. S. Imran, and Z. Kastrati, “Aspect-based sentiment analysis for software requirements elicitation using fine-tuned Bidirectional Encoder Representations from Transformers and Explainable Artificial Intelligence,” Engineering Applications of Artificial Intelligence, vol. 151, article 110632, 2025, doi: 10.1016/j.engappai.2025.110632.
Md. A. Talukder et al., “A hybrid deep learning model for sentiment analysis of COVID-19 tweets with class balancing,” Sci Rep, vol. 15, no. 1, p. 27788, Jul. 2025, doi: 10.1038/s41598-025-97778-7.
K. L. Tan, C. P. Lee, K. S. M. Anbananthen, and K. M. Lim, “RoBERTa-LSTM: A Hybrid Model for Sentiment Analysis With Transformer and Recurrent Neural Network,” IEEE Access, vol. 10, pp. 21517–21525, 2022, doi: 10.1109/ACCESS.2022.3152828.
V. Varadharajan, N. Smith, D. Kalla, F. Samaah, and V. Mandala, “Deep Learning-Based Sentiment Analysis: Enhancing IMDb Review Classification with LSTM Models,” UJCSC, vol. 4, no. 1, pp. 1–14, Jan. 2025, doi: 10.31586/ujcsc.2025.1249.
J. Wang, S. Wang, and Y. Zhang, “Deep learning on medical image analysis,” CAAI Trans on Intel Tech, vol. 10, no. 1, pp. 1–35, Feb. 2025, doi: 10.1049/cit2.12356.
M. Wankhade, A. C. S. Rao, and C. Kulkarni, “A survey on sentiment analysis methods, applications, and challenges,” Artif Intell Rev, vol. 55, no. 7, pp. 5731–5780, Oct. 2022, doi: 10.1007/s10462-022-10144-1.
L. Xiaoyan, R. C. Raga, and S. Xuemei, “GloVe-CNN-BiLSTM Model for Sentiment Analysis on Text Reviews,” Journal of Sensors, vol. 2022, pp. 1–12, Oct. 2022, doi: 10.1155/2022/7212366.
W. Xu, J. Chen, Z. Ding, and J. Wang, “Text sentiment analysis and classification based on bidirectional Gated Recurrent Units (GRUs) model,” ACE, vol. 77, no. 1, pp. 132–137, July 2024, doi: 10.54254/2755-2721/77/20240670.
H. Zhang, J. Xu, L. Lei, Q. Jianlin, and R. Alshalabi, “A Sentiment Analysis Method Based on Bidirectional Long Short-Term Memory Networks,” Applied Mathematics and Nonlinear Sciences, vol. 8, no. 1, pp. 55–68, Jan. 2023, doi: 10.2478/amns.2022.1.00015
Downloads
Published
Issue
Section
License
Copyright (c) 2026 International Innovations Journal of Applied Science
This work is licensed under a Creative Commons Attribution 4.0 International License.
