Sentiment Analysis of Customers in Iran’s Automotive Industry Using the LSTM Method
Keywords:
Sentiment analysis, automotive industry customers, Iran, LSTM, SMOTE, Data AugmentationAbstract
Given the large volume of customer opinions and complaints regarding automobiles in Iranian virtual platforms, this study aimed to develop an accurate sentiment analysis model based on Long Short-Term Memory (LSTM) neural networks for processing Persian texts. The primary objective was to improve the accuracy of sentiment classification (positive, negative, and neutral) by overcoming the challenges associated with imbalanced data and linguistic limitations. Data were collected from 12 valid online sources, including 4,348 customer comments regarding various automobile models. Three LSTM architectures (single-layer, two-layer, and three-layer) were implemented and compared using fixed parameters (Embedding = 128, Hidden Units = 64, Dropout = 0.3). To enhance performance, Data Augmentation, the SMOTE algorithm, and FastText word embeddings were employed. The three-layer LSTM model outperformed the shallower models, achieving a validation accuracy of 62.01%, which increased to 95.45% after applying optimization techniques. The two-layer model demonstrated superior performance in identifying positive comments, whereas the three-layer model showed a more balanced performance across all sentiment classes. The issue of overfitting in simpler models was mitigated through the addition of layers and the use of Dropout. The findings indicated that the two-layer model improved overall accuracy, particularly in recognizing positive sentiments, compared to the single-layer model. Furthermore, the three-layer LSTM model demonstrated greater balance and robustness across all classes. To further improve performance, the three-layer model was retrained using Data Augmentation techniques and the SMOTE algorithm for data balancing. The modified version substantially improved overall accuracy and validation performance.
References
Amjadian, P. (2024). Remaining Useful Life Estimation of Bearings Using Vibration Signal Processing Based on Continuous Wavelet Transform and LSTM Deep Learning Network. Transactions on Machine Intelligence, 7(1), 61-69. https://doi.org/10.47176/TMI.2024.61
Birjali, M., Kasri, M., & Beni-Hssane, A. (2021). A Comprehensive Survey on Sentiment Analysis: Approaches, Challenges and Trends. Knowledge-Based Systems, 226, 107134.
Dam, M., Roy, S., Sarkar, D., & Mahata, S. K. (2025). Sentiment Analysis Using LSTM Model for Emotion Detection. Kolkata, India.
Farajzadeh, K., Taghavifard, M. T., Toloei Ashlaghi, A., & Rashidi Komijan, A. (2023). Sentiment Analysis Based on Text Mining in the Social Network Twitter to Understand People's Thinking. New Media Studies, 9(34), 1-32. https://doi.org/10.22054/nms.2023.69807.1453
Hossain, M. S. (2024). Textual Feature Engineering for Purchase Intent and Customer Satisfaction: Insights from Marketing 4.0 and Sentiment. Sustainable Futures, 8, 100385.
Huang, B., Guo, R., Zhu, Y., Fang, Z., Zeng, G., Liu, J., Wang, Y., Fujita, H., & Shi, Z. (2022). Aspect-Level Sentiment Analysis with Aspect-Specific Context Position Information. Knowledge-Based Systems, 243, 108473.
Karimi Dastgerdi, A., & Zamani Boroujeni, F. (2020). A Review of Deep Learning Methods for Financial Market Prediction. Transactions on Data Analysis in Social Science, 2(3), 164-172. https://doi.org/10.47176/TDASS.2020.164
Kazemi, E., Sadeghzadeh, M., & Taeizadeh, A. (2023). Presenting a New Sentiment Analysis Method Based on Multi-Objective Archimedes Optimization Algorithm and Machine Learning. Electronic and Cyber Defense, 11(4), 145-153.
Lin, Y., & Jen, L. (2024). The Impact of Consumer Heterogeneity in the Product Life Cycle on the Diffusion Patterns of User Reviews and Sales. Journal of Retailing and Consumer Services.
Mao, Y., Liu, Q., & Zhang, Y. (2024). Sentiment Analysis Methods, Applications, and Challenges: A Systematic Literature Review. Journal of King Saud University - Computer and Information Sciences, 36(4), 102048.
Mehrkian, S. S., & Davari-Ardakani, H. (2025). An Integrated Model of Sentiment Analysis and Quantitative Index Data for Predicting Stock Market Trends: A Case Study of Tehran Stock Exchange. Expert Systems with Applications, 269, 126298.
Mirzaee, A., Zeynali, M., Ghorbanzadeh, A., & Ghorbanzadeh, P. (2024). Personal Recommender Model and Predicting Consumer Behavior in Digital Marketing Based on Deep Learning. Transactions on Machine Intelligence, 7(3), 179-193. https://doi.org/10.47176/TMI.2024.179
Mohammadi, M. (2023). Presenting a Predictive Model for Sentiment Analysis of Users toward the City Based on the Twitter Social Network: A Case Study of Iranian Metropolises. Iranian Architecture and Urbanism, 14(2), 301-317.
Prasastio, F. R., Pradana, P. D. R., Permana, E., Afiahayati, & Frisky, A. Z. K. (2024). Sentiment Analysis of Electric Vehicle Incentives Using CNN-LSTM and SVM Models. Medan, Indonesia.
Puh, K., & Bagic Babac, M. (2023). Predicting Sentiment and Rating of Tourist Reviews Using Machine Learning. Journal of Hospitality and Tourism Insights, 6(3), 1188-1204.
Ricchiuti, F., & Sperli, G. (2025). An Advisor Neural Network Framework Using LSTM-Based Informative Stock Analysis. Expert Systems with Applications, 259, 125299.
Rodriguez-Ibanez, M., Casanez-Ventura, A., Castejon-Mateos, F., & Cuenca-Jimenez, P. M. (2023). A Review on Sentiment Analysis from Social Media Platforms. Expert Systems with Applications, 119862.
Selimovic, M., Abd Almisreb, A., & Amanzholova, S. (2024). The Role of Sentiment Analysis in Brand Management and Marketing: A Comparative Study. Procedia Computer Science, 251, 579-584.
Sudirjo, F., Diantoro, K., Al-Gasawneh, J. A., Azzaakiyyah, H. K., & Ausat, A. M. A. (2023). Application of ChatGPT in Improving Customer Sentiment Analysis for Businesses. Jurnal Teknologi Dan Sistem Informasi Bisnis, 5, 283-288.
Susnjak, T. (2024). Applying BERT and ChatGPT for Sentiment Analysis of Lyme Disease in Scientific Literature. Methods and Protocols, 173-183.
Wang, H., & Zheng, L. (2016). Sentiment Classification of Chinese Online Reviews: A Comparison of Factors Influencing Performances. Enterprise Information Systems, 10, 228-244.
Wen, Z., Chen, Y., Liu, H., & Liang, Z. (2024). Text Mining Based Approach for Customer Sentiment and Product Competitiveness Using Composite Online Review Data. Journal of Theoretical and Applied Electronic Commerce Research, 19, 1776-1792. https://doi.org/10.3390/jtaer19030087
Downloads
Published
Submitted
Revised
Accepted
Issue
Section
License
Copyright (c) 2026 Lida Shojaei Barjouei (Author); Ghasem Bakhshandeh; Mahmood Daniali Deh houz (Author)
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
