A Hybrid CNN-LSTM Based Natural Language Processing Model for Sentiment Analysis of Customer Product Reviews: A Case Study from Ghana

Nouhaila El Koufi, Yaw Marfo Missah, Abdessamad Belangour

Abstract

As new technologies rapidly evolve and consumer habits and lifestyles change, there is a noticeable shift toward online shopping and services among customers. Consequently, there has been a consistent surge in the volume of customer data. A significant portion of these data revolves around consumers’ perceptions and opinions regarding organizations’ products or services. This study aims to develop a novel hybrid CNN-LSTM model to analyze customer sentiment and satisfaction with e-commerce platforms. By integrating deep learning techniques with sentiment analysis and natural language processing, this approach offers a comprehensive system capable of understanding consumer feedback with greater accuracy. The purpose is to create a robust tool for precision marketing that not only captures customer sentiments, but also enhances decision-making in e-commerce. These data are of considerable importance for market intelligence collectors operating in areas such as marketing, customer relationship management, and customer retention. Sentiment analysis is employed to scrutinize customer sentiment, marketing campaigns, and product evaluations, thus assisting e-commerce companies in acquiring a more profound understanding of their customers’ viewpoints and satisfaction with a product or service. This valuable insight can help managers improve their decision-making regarding future products and services, marketing strategies, promotional channels, and customer service improvements. By harnessing artificial intelligence techniques, such as deep learning, sentiment analysis, and natural language processing, it becomes possible to create and implement systems capable of analyzing consumer satisfaction and feedback on e-commerce platforms. The novelty of this study lies in its innovative combination of CNN and LSTM architectures, which allows the model to effectively capture both spatial and temporal patterns in textual data, providing deeper insights into consumer behavior than traditional methods. A case study was conducted using authentic data from an e-commerce enterprise in Ghana to demonstrate the practical application of our approach. The research findings revealed that the suggested model yielded positive results. The proposed hybrid CNN-LSTM model is applied to target marketing to obtain precise consumer profiles and enhance decision-making, with the aim of increasing enterprise revenue.

 

Keywords: artificial intelligence; decision-making; deep learning; natural language processing; e-commerce

 

https://doi.org/10.55463/issn.1674-2974.51.8.5

 


Full Text:

PDF


References


EL KOUFI N., & BELANGOUR A. Toward a responsive system for precision marketing based on RFM model, deep learning and features importance ranking: a case study of Morocco. International Journal of Advanced Computer Science Applications, 2024, 16(2): 1-10.‏

BAI X., AW E. C. X., TAN G. W. H., & OOI K. B. Livestreaming as the next frontier of e-commerce: A bibliometric analysis and future research agenda. Electronic Commerce Research and Applications, 2024, 110(2): 1-10.‏ https://doi.org/10.1016/j.elerap.2024.101390

CHEN H., LI H., & PIRKKALAINEN H. How extended reality influences e-commerce consumers: A literature review. Electronic Commerce Research and Applications, 2024, 10(14): 1-13. https://doi.org/10.1016/j.elerap.2024.101404

EL KOUFI N., BELANGOUR A., & SADIQ M. A systematic literature review of machine learning techniques applied to precision marketing. Technical and Physical Problems of Engineering, 2022, 14(7): 1-7.

ZAGHLOUL M., BARAKAT S., & REZK A. Predicting E-commerce customer satisfaction: Traditional machine learning vs. deep learning approaches. Journal of Retailing and Consumer Services, 2024, 79(33): 1-17. https://doi.org/10.1016/j.jretconser.2024.103865

EL KOUFI N., BELANGOUR A., & SADIQ M. Research on precision marketing based on big data analysis and machine learning: case study of Morocco. International Journal of Advanced Computer Science and Applications, 2022, 13(10): 1-8.

EL KOUFI N., & BELANGOUR A. Research intelligent precision marketing of insurance based on explainable machine learning: a case study of an insurance company. Journal of Theoretical and Applied Information Technology, 2024, 102(6): 1-14. http://dx.doi.org/10.14569/IJACSA.2022.0131008

ALMUTAIRI S. M., & ALOTAIBI F. M. A Comparative Analysis for Arabic Sentiment Analysis Models In E-Marketing Using Deep Learning Techniques. Journal of Engineering and Applied Sciences, 2024, 10(1): 1-13. https://doi.org/10.5455/jeas.2023050102

RAVIYA K., & VENNILA M. An approach for recommender system based on multilevel sentiment analysis using hybrid deep learning models. International Conference on Smart Structures and Systems (ICSSS), IEEE, 2022, 13(4):1-06.

RAJU B., SRIRAM M., & GANESAN V. Optimized deep learning model for sentimental analysis to improve consumer experience in ecommerce websites. Journal of Theoretical and Applied Information Technology, 2024, 102(7):1-14.

LUO Y., & XU X. Comparative study of deep learning models for analyzing online restaurant reviews in the era of the COVID-19 pandemic. International Journal of Hospitality Management, 2021, 94(34):1-19.

GIATSOGLOU M., VOZALIS M. G., DIAMANTARAS K., VAKALI A., SARIGIANNIDIS G., & CHATZISAVVAS K. C. Sentiment analysis leveraging emotions and word embeddings. Expert Systems with Applications, 2017, 69(20): 214-224.

DANG N. C., MORENO-GARCÍA M. N., & DE LA PRIETA F. Sentiment analysis based on deep learning: A comparative study. Electronics, 2020, 9(3): 1-8.

FAN Z. P., CHE Y. J., & CHEN Z. Y. Product sales forecasting using online reviews and historical sales data: A method combining the Bass model and sentiment analysis. Journal of Business Research, 2017, 74(30): 1-10.

PRIYADARSHINI I., & COTTON C. A novel LSTM–CNN–grid search-based deep neural network for sentiment analysis. The Journal of Supercomputing, 2021, 77(12): 1-20.

ALZAHRANI M. E., ALDHYANI T. H., ALSUBARI S. N., ALTHOBAITI M. M., & FAHAD A. Developing an Intelligent System with Deep Learning Algorithms for Sentiment Analysis of E-Commerce Product Reviews. Computational Intelligence and Neuroscience, 2022, 2022(1): 1-21.

ZHU H. A deep learning based hybrid model for sales prediction of e-commerce with sentiment analysis. International Conference on Computing and Data Science (CDS), IEEE, 2021, 30(5): 1-9.

YANG L., LI Y., WANG J., & SHERRATT R. S. Sentiment analysis for E-commerce product reviews in Chinese based on sentiment lexicon and deep learning. IEEE Access, 2020, 8(5): 1-20.

IQBAL A., AMIN R., IQBAL J., ALROOBAEA R., BINMAHFOUDH A., & HUSSAIN M. Sentiment analysis of consumer reviews using deep learning. Sustainability, 2020, 14(17): 1-9.

SHOJA B. M., & TABRIZI N. Customer reviews analysis with deep neural networks for e-commerce recommender systems. IEEE Access, 2019, 7(3): 1-30.

KAUR G., & SHARMA A. A deep learning-based model-using hybrid feature extraction approach for consumer sentiment analysis. Journal of Big Data, 2023, 10(1): 1-5.

SARI P. K., ALAMSYAH A., & WIBOWO S. Measuring e-Commerce service quality from online customer review using sentiment analysis. Journal of Physics: Conference Series, 2018, 971(54): 1-20.

XU F., PAN Z., & XIA R. E-commerce product review sentiment classification based on a naïve Bayes continuous learning framework. Information Processing & Management, 2020, 57(5): 1-21. https://doi.org/10.1016/j.ipm.2020.102221

YADAV V., VERMA P., & KATIYAR V. Long short term memory (LSTM) model for sentiment analysis in social data for e-commerce products reviews in Hindi languages. International Journal of Information Technology, 2023, 15(2): 759-772.

EL KOUFI N., & BELANGOUR A. Artificial Intelligence Techniques in Precision Marketing: A Multi-criteria Analysis and Comparative Study. International Conference on Computing, Intelligence and Data Analytics, Springer, 2023, 2(1): 1-7.

EL KOUFI N., & BELANGOUR A. Toward a decision-making system based on artificial intelligence for precision marketing: A case study of Morocco. Journal of Open Innovation: Technology, Market, and Complexity, 2024, 10(1): 1-20. https://doi.org/10.1016/j.joitmc.2024.100250

EL KOUFI N., & BELANGOUR A. Artificial intelligence techniques applied in precision marketing: a survey. International Conference on Electrical, Computer, Communications and Mechatronics Engineering, IEEE, 2024, 13(6): 1-5. https://doi.org/10.1109/ICECCME57830.2023.10253083


Refbacks

  • There are currently no refbacks.