Comparison of the Performance of a Three-Layer LSTM Model with Classical Algorithms in Sentiment Analysis of Persian Texts in the Automotive Industry
Keywords:
Sentiment analysis, LSTM, classical machine learning, automotive industry, Persian textsAbstract
In the field of business, sentiment analysis is considered an effective tool for monitoring customer feedback, improving decision-making processes, and enhancing product quality. This study aimed to evaluate the efficiency of different sentiment analysis methods by comparing the performance of a deep learning model based on a three-layer Long Short-Term Memory (LSTM) recurrent neural network with four classical machine learning algorithms, including Linear Support Vector Machine (Linear SVM), Naive Bayes, Multilayer Perceptron (MLP), and Decision Tree. The research data consisted of real user reviews regarding domestic automobiles, which were utilized for model training and evaluation after standard preprocessing procedures. The findings indicated that among the classical algorithms, the Linear SVM model achieved the best performance with an accuracy of 0.90, followed by the MLP model with an accuracy of 0.88, whereas the Naive Bayes and Decision Tree models demonstrated the weakest performance. Compared with these methods, the three-layer LSTM model significantly outperformed the other approaches by achieving an accuracy of 95.4%. This superiority can be attributed to the capability of the LSTM architecture to learn temporal dependencies, capture the sequential structure of sentences, and extract deeper semantic relationships.
References
[1] M. Birjali, M. Kasri, and A. Beni-Hssane, "A Comprehensive Survey on Sentiment Analysis: Approaches, Challenges and Trends," Knowledge-Based Systems, vol. 226, p. 107134, 2021.
[2] M. Rodriguez-Ibanez, A. Casanez-Ventura, F. Castejon-Mateos, and P. M. Cuenca-Jimenez, "A Review on Sentiment Analysis from Social Media Platforms," Expert Systems with Applications, p. 119862, 2023.
[3] W. Khan, A. Daud, K. Khan, S. Muhammad, and R. Haq, "Exploring the Frontiers of Deep Learning and Natural Language Processing: A Comprehensive Overview of Key Challenges and Emerging Trends," Natural Language Processing Journal, vol. 4, p. 100026, 2023.
[4] R. Patil and V. Gudivada, "A Review of Current Trends, Techniques, and Challenges in Large Language Models (LLMs)," Applied Sciences, vol. 14, p. 2074, 2024.
[5] F. Sudirjo, K. Diantoro, J. A. Al-Gasawneh, H. K. Azzaakiyyah, and A. M. A. Ausat, "Application of ChatGPT in Improving Customer Sentiment Analysis for Businesses," Jurnal Teknologi dan Sistem Informasi Bisnis, vol. 5, pp. 283-288, 2023.
[6] J. Chen, "When Large Language Models Meet Personalization: Perspectives of Challenges and Opportunities," World Wide Web, vol. 27, p. 42, 2024.
[7] E. Georgiadou, S. Angelopoulos, and H. Drake, "Big Data Analytics and International Negotiations: Sentiment Analysis of Brexit Negotiating Outcomes," International Journal of Information Management, vol. 51, p. 102048, 2020.
[8] S. S. Mehrkian and H. Davari-Ardakani, "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, vol. 269, p. 126298, 2025.
[9] P. N. Lopez et al., "Detection of Occupant Emotion in Automated Vehicles under Different Driving Conditions," Transportation Research Procedia, vol. 72, pp. 3917-3924, 2023.
[10] B. Palomares-Nicolas et al., "Detection of Occupant Emotion in Automated Vehicles under Different Driving Conditions," Transportation Research Procedia, vol. 72, pp. 3917-3924, 2023.
[11] M. Oehl, A. A. Pape, K. Ihme, M. Vukelic, E. Bosch, and M. Braun, "Emotions in the Age of Automated Driving," 2019.
[12] C. Nadri et al., "Empathic Vehicle Design: Use Cases and Design Directions from Two Workshops," 2022, pp. 1-7.
[13] T. Y. Kim, H. Ko, and S. H. Kim, "Data Analysis for Emotion Classification Based on Bio-Information in Self-Driving Vehicles," Journal of Advanced Transportation, 2020.
[14] I. I. Barosan, "CarESP: An Emotional Vehicle with Stress, Personality and Embodiment of Emotions," 2020.
[15] R. Bose, R. K. Dey, S. Roy, and D. Sarddar, "Sentiment Analysis on Online Product Reviews," Springer, 2020, pp. 559-569.
[16] T. Ahmed, M. Rahman, S. Nur, A. Islam, and D. Das, "Deployment of Machine Learning and Deep Learning Algorithms in Detecting Cyberbullying in Bangla and Romanized Bangla Text: A Comparative Study," 2021, doi: 10.1109/icaect49130.2021.9392608.
[17] M. Rahman, S. Haque, and Z. Rahman, "Identifying and Categorizing Opinions Expressed in Bangla Sentences Using Deep Learning Technique," International Journal of Computer Applications, vol. 176, no. 17, pp. 13-17, 2020, doi: 10.5120/ijca2020920119.
[18] M. Dam, S. Roy, D. Sarkar, and S. K. Mahata, "Sentiment Analysis Using LSTM Model for Emotion Detection," Kolkata, India, 2025, pp. 1-5, doi: 10.1109/IEMENTech65115.2025.10959455.
[19] F. Ricchiuti and G. Sperli, "An Advisor Neural Network Framework Using LSTM-Based Informative Stock Analysis," Expert Systems with Applications, vol. 259, p. 125299, 2025.
[20] F. Z. Xing, E. Cambria, and R. E. Welsch, "Natural Language-Based Financial Forecasting: A Survey," Artificial Intelligence Review, vol. 50, pp. 49-73, 2018.
[21] A. Mirzaee, M. Zeynali, A. Ghorbanzadeh, and P. Ghorbanzadeh, "Personal Recommender Model and Predicting Consumer Behavior in Digital Marketing Based on Deep Learning," Transactions on Machine Intelligence, vol. 7, no. 3, pp. 179-193, 2024, doi: 10.47176/TMI.2024.179.
[22] M. S. Hossain, "Textual Feature Engineering for Purchase Intent and Customer Satisfaction: Insights from Marketing 4.0 and Sentiment," Sustainable Futures, vol. 8, p. 100385, 2024.
[23] I. H. Sarker, M. H. Furhad, and R. Nowrozy, "AI-Driven Cybersecurity: An Overview, Security Intelligence Modeling, and Research Directions," SN Computer Science, vol. 2, no. 3, 2021, doi: 10.1007/s42979-021-00557-0.
[24] T. Susnjak, "Applying BERT and ChatGPT for Sentiment Analysis of Lyme Disease in Scientific Literature," 2024, pp. 173-183.
[25] B. Huang et al., "Aspect-Level Sentiment Analysis with Aspect-Specific Context Position Information," Knowledge-Based Systems, vol. 243, p. 108473, 2022.
[26] H. T. Phan, N. T. Nguyen, and D. Hwang, "Aspect-Level Sentiment Analysis: A Survey of Graph Convolutional Network Methods," Information Fusion, vol. 91, pp. 149-172, 2023.
[27] A. Kazance, R. Ventura, and J. Smith, "Deep Learning-Based Sentiment Analysis for Persian User Reviews," Expert Systems with Applications, vol. 225, p. 119862, 2023, doi: 10.1016/j.eswa.2023.119862.
[28] A. Achour, M. A. Kammoun, and Z. Hajej, "Towards Optimizing Multi-Level Selective Maintenance via Machine Learning Predictive Models," Applied Sciences, vol. 14, p. 313, 2023.
[29] P. Amjadian, "Remaining Useful Life Estimation of Bearings Using Vibration Signal Processing Based on Continuous Wavelet Transform and LSTM Deep Learning Network," Transactions on Machine Intelligence, vol. 7, no. 1, pp. 61-69, 2024, doi: 10.47176/TMI.2024.61.
[30] L. Rognone, S. Hyde, and S. S. Zhang, "News Sentiment in the Cryptocurrency Market: An Empirical Comparison with Forex," International Review of Financial Analysis, vol. 69, p. 101462, 2020.
[31] Q. Zhang, K. Yang, Y. Hu, J. Jiao, and S. Wang, "Unveiling the Impact of Geopolitical Conflict on Oil Prices: A Case Study of the Russia-Ukraine War and Its Channels," Energy Economics, vol. 126, p. 106956, 2023.
[32] M. R. Baker, Y. N. Taher, and K. H. Jihad, "Prediction of People Sentiments on Twitter Using Machine Learning Classifiers during Russian Aggression in Ukraine," Jordanian Journal of Computers & Information Technology, vol. 9, 2023.
[33] K. H. Jihad, M. R. Baker, M. Farhat, and M. Frikha, "Machine Learning-Based Social Media Text Analysis: Impact of Rising Fuel Prices on Electric Vehicles," 2022, pp. 625-635.
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Lida Shojaei Barjouei (Author); Ghasem Bakhshandeh (Corresponding author); Mahmood Daniali Deh houz (Author)
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
