Customer Reviews Classification with Text Mining and Deep Learning Approach (Case Study: Digikala Customers Reviews)

Document Type : Research Paper


Msc. Student, Department of Computer Engineering, Faculty of Computer Engineering, Shahid Bahonar University of Kerman, Kerman, Iran.


Today, people face different decision-making criteria when purchasing products and services. One of these criteria is using the reviews of the previous purchasers of products and services. A large volume of reviews is seen as a challenge for these people. The present study aimed to create a model to analyze users’ sentiments and to classify their reviews to solve the mentioned challenge.
The present study investigated the buyers’ reviews of mobile phones purchased on the Digikala Website from 2015 to 2016. To analyze the sentiments, and to classify the reviews, deep learning-based algorithms, and convolutional networks, subtypes of deep networks, were suggested. Prior to preprocessing and homogenizing the data, the study used a pre-trained Fastext model to convert the words into integer vectors and deliver them as inputs to the proposed deep network.
To train the selected model, the training algorithm was carried out on it 90 times. To validate the performance of the selected model, confusion matrix, accuracy, recall, F1-score, and precision rate criteria were used.
The present study used the deep networks approach, convolutional networks, and bidirectional long short-term memory to classify the buyers’ reviews of the mobile phone from the website above at 93% accuracy, and after 90 training periods.


Abbasi, F., Khadivar, A. & Yazdinezhad, M. (2020). Sentiment analysis of the Digikala Iphone buyers reviews. IT Management Studies, 8(32), 181-210. (in Persian)
Abbasi, F., Sohrabi, B., Khadivar, A. & Yazdinezhad, M. (2019). Presenting a model to classify book buyers using hybrid method. IT Management Studies, 8(32), 181 - 210. (in Persian)
Almutairi, Y., & Abdullah, M. (2020). IRHM: Inclusive Review Helpfulness Model for Review Helpfulness Prediction in E-commerce Platform. Journal of Information Technology Management, 12(2), 184-197.
Bakhshizadeh Borj, K., Haji Jafar, A., & Nasiri, H. (2018). Eliciting Mental Map of the Customers of Digikala E-Stores Using Zaltman Metaphor Elicitation Technique (ZMET). Journal of Business Management10(1), 49-72. (in Persian)
Deng, L. & Yu, D. (2014). Deep Learning: Methods and Applications. Foundations and Trends® in Signal Processing, 7(3–4), 197–387. doi:10.1561/2000000039
Edalat, M. H., Azmi, R. & Bagherinezhad, J. (2020). An Enhanced LSTM Method to Improve the Accuracy of the Business Process Prediction. Industrial Management Perspective, 10(3), 71-97. (in Persian)
Fang, X. & Zhan, J. (2015). Sentiment analysis using product review data. Journal of Big Data, 2(5), 1 - 14.
Filho, P. & Pardo, T. (2013). An Improved Hybrid System for Sentiment Analysis in Twitter Messages. Second Joint Conference on Lexical and Computational Semantics (*SEM), 568-572.
Haghighi, M., Aghazadeh, H., Khodadad Hosseini, S., Gharibi, M. (2019). Explaining the Dimension of Competitive Intelligence through Utilizing Social Media Capabilities in Iran Non-Alcoholic Beverage Industry. Journal of Business Management, 11(4), 742-761. (in Persian)
Hochreiter, S. & Schmidhuber, J. (1997). Long Short-term Memory. Neural Computation, 9(8), 1735–1780.
Liu, B. (2012). Sentiment Analysis and Opinion Mining. Synthesis Lectures on Human Language Technologies.
Liu, B. (2015). Sentiment analysis: Mining opinions, sentiments, and emotions. Cambridge University Press.
Mojumder, P., Hasan, M., Hossain, Md. F., & Hasan, K. M. A. (2020). A Study of fastText Word Embedding Effects in Document Classification in Bangla Language. In T. Bhuiyan, Md. M. Rahman, & Md. A. Ali (Eds.), Cyber Security and Computer Science (pp. 441–453). Springer International Publishing.
Mousavi, S., Amiri Aghdaie, S. (2021). Identifying the Constructive Elements of “Value Proposition” and their Impact on Customers’ Satisfaction using Sentiment Analysis based on Text Mining. Journal of Business Management, 12(4), 1092-1116. doi: 10.22059/jibm.2020.302987.3847. (in Persian)
Murugavalli, S., Bagirathan, U., Saiprassanth, R., & Arvindkumar, S. (2017). Feedback analysis using Sentiment Analysis for E- commerce. International Journal of Latest Engineering Research and Applications (IJLERA), 2(3), 84-90.
Najafzadeh, M., Rahati Ghouchani, S. & Ghaemi, R. (2018). A Semi-supervised Framework Based on Self-constructed Adaptive Lexicon for Persian Sentiment Analysis. Signal and Data Processing, 15(2), 89 - 102. (in Persian)
Niknam, F., & Niknafs, A. (2016). Improving Text Mining Methods in Market Prediction via Prototype Selection Algorithms. Journal of Information Technology Management (JITM), 8(2), 415 - 434. (in Persian)
Pandey, A. C., Rajpoot, D. S. & Saraswat, M. (2017). Twitter sentiment analysis using hybrid cuckoo search method. Information Processing & Management, 53(4), 764 - 799.
Peykari, N., Yaghoubi, S. A. & Taheri, H. (2015). Sentiment analysis in twitter using data mining method. International Conference on Web Research. (in Persian)
Poursaeed, M., Shojaee, F., Niknafs, A. (2021). The Factors Affecting Place Branding based on Data Mining Approach (Case Study: Instagram Social Media). Journal of Business Management, 13(2), 473-501. doi: 10.22059/jibm.2021.309977.3944. (in Persian)
Qayyum, A., Anwar, S. M., Awais, M. & Majid, M. (2017). Medical Image Retrieval using Deep Convolutional Neural Network. Neurocomputing, 266, 8-20.
Raghavan, V., Gwang, J. (1989). A Critical Investigation of Recall and Precision as Measures of Retrieval System Performance. ACM Transactions on Information Systems, 7(3), 205-229.
Saniee Abade, M., Mahmoudi, S. & Taherparvar, M. (2015). Applied data mining. (in Persian)
Sezavar, A., Farsi, H. & Mohammadzadeh, S. (2019). Content-Based Image Retrieval using Deep Convolutional Neural Networks. Tabriz Journal of Electrical Engineering (TJEE), 48(4), 1595-1603. (in Persian)
Tavakoli garmase, A. & Rafe, V. (2016). Presenting a method to analyze sentiments in reveiws texts. First National Conference on Industrial Engineering & Systems. (in Persian)
Wang, Z. (2017). The Evaluation of Ensemble Sentiment Classification Approach on Airline Services Using Twitter. Masters dissertation, Technological University Dublin, 2017. doi:10.21427/D7190M.
Yu, L., Wang, J., Lai, K., Xhang, X,. (2017) Refining Word Embeddings for Sentiment Analysis. Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing.
Zhang, Y., Ren, W., Zhu, T. & Faith, E. (2019). MoSa: A Modeling and Sentiment Analysis System for Mobile Application Big Data. Symmetry, 11(1), 115.