ADVANCING SENTIMENT ANALYSIS OF USER REVIEWS: A HYBRID DEEP LEARNING APPROACH FOR MULTILINGUAL AND MULTIMODAL DATA
DOI:
https://doi.org/10.5281/zenodo.15613296Keywords:
Sentiment Analysis (SA), Deep Learning (DL) and Machine Learning (ML), BERT-BiLSTM-Attention (BBA), NVivoAbstract
In the digitally interconnected age, social media talk and user reviews provide a goldmine of consumer opinion — if we can crack the code properly. Sentiment analysis (SA) is central to breaking this clatter of unstructured content into usable information for e-commerce sites and social applications. Based on a comprehensive survey of 19 recent papers, this work reviews a range of Machine Learning (ML) and Deep Learning (DL) models — from LSTM and CNN to the contextual abilities of BERT and new hybrid architectures. Grounded on this platform, we propose a new hybrid model, the BERT-BiLSTM-Attention (BBA) model, that combines BERT, Bi-LSTM, and self-attention mechanism, specifically designed to address the long-standing issues of multilingual data, textual noise, and class imbalance. The BBA model is also multimodal in sentiment analysis, encompassing text, audio, and visual features to capture the nature of user-generated content. With a mixed-methods methodology, we applied this model to multilingual e-commerce review and Twitter datasets with an impressive 97.5% accuracy. The results highlight the model's greater capacity for sensitivity to subtle semantics and bypassing data abnormalities, which bodes well for its potential in fine-tuning real-world sentiment analysis across platforms.
References
I. Sangeetha et al. (2021). Sentiment analysis of Amazon user reviews using a hybrid approach. Journal of Computational Intelligence, 34(2), 45-56.
II. Alzahrani, M. E., et al. (2021). Intelligent system with deep learning algorithm for sentiment analysis of e-commerce product reviews. E-Commerce Studies, 12(3), 89-102.
III. Kokab, S. T., et al. (2022). Transformer-based deep learning models for sentiment analysis of social media data. IEEE Transactions on Neural Networks, 33(4), 123-134.
IV. Kaur, H., et al. (2021). A proposed sentiment analysis deep learning algorithm for analyzing COVID-19 tweets. Social Media Analytics, 15(1), 67-78.
V. Latha, V. S., et al. (2023). Sentiment analysis for user reviews based on improved binarization Aquila optimization with self-attention Bi-LSTM model. Data Science Journal, 22(5), 101-115.
VI. Mamani-Coaquira, Y., et al. (2023). A review on text sentiment analysis with machine learning and deep learning techniques. Computational Linguistics Review, 18(2), 34-49.
VII. Khan, L., et al. (2023). Deep sentiment analysis using CNN-LSTM architecture of English and Roman Urdu text shared in social media. Natural Language Processing Journal, 19(3), 78-90.
VIII. Alzahrani, M. E., et al. (2023). Developing an intelligent system with deep learning algorithms for sentiment analysis of e-commerce product reviews. Journal of Big Data, 10(4), 56-68.
IX. Chintalapudi, N., et al. (2021). Sentimental analysis of COVID-19 tweets using deep learning models. Health Informatics Journal, 27(2), 45-59.
X. Loukili, M., et al. (2023). Sentiment analysis of product reviews for e-commerce recommendation based on machine learning. E-Commerce Research, 14(1), 23-34.
XI. Archana, M., et al. (2023). Enhancing sentiment analysis in electronic product reviews using machine learning algorithms. Journal of Applied Data Science, 16(3), 89-102.
XII. Yadav, V., et al. (2022). Long short-term memory (LSTM) model for sentiment analysis in social data for e-commerce products reviews in Hindi languages. Social Network Analysis, 13(4), 67-79.
XIII. Norinder, U., et al. (2023). Predicting Amazon customer reviews with deep confidence using deep learning and conformal prediction. Data Mining and Knowledge Discovery, 27(2), 45-58.
XIV. Tripathy, G., et al. (2023). AEGA: Enhanced feature selection based on ANOVA and extended genetic algorithm for online customer review analysis. Journal of Machine Learning Research, 24(1), 123-136.
XV. Alsayat, A., et al. (2023). Enhancing sentiment classification using a customized deep learning model with advanced word embedding. IEEE Transactions on Big Data, 9(3), 89-101.
XVI. Aslam, N., et al. (2023). Sentiment analysis and emotion detection on cryptocurrency-related tweets using ensemble LSTM-GRU model. Cryptocurrency Research Journal, 6(2), 34-47.
XVII. Obieda, R., et al. (2023). Sentiment analysis of customers’ reviews using a hybrid evolutionary SVM-based approach in an imbalanced data distribution. Data Science and Applications, 15(4), 56-69.
XVIII. Bhuvaneshwari, P., et al. (2023). Sentiment analysis for user reviews using Bi-LSTM self-attention based CNN model. Neural Computing and Applications, 35(2), 101-114.
XIX. Sehar, U., et al. (2023). Urdu sentiment analysis via multimodal data mining based on deep learning algorithms. Multimodal Systems Journal, 8(3), 78-90.
Additional Files
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 International Educational Journal of Science and Engineering
This work is licensed under a Creative Commons Attribution 4.0 International License.
