Data Centric Blockchain Based Evaluation Approach to Analyze E-Commerce Reviews Using Machine and Deep Learning Techniques

Machine and deep learning techniques are now essential for many different kinds of solutions in many areas, applications, and businesses. Analyzing e-commerce reviews using machine and deep learning techniques can motivate a company to make more wise decisions regarding the quality and services it offers. But issues can occur if there is insufficient high-quality data for the training, scalability, and upkeep of learning models. To address these important issues, we suggest a data-centric learning architecture that makes use of a blockchain and Interplanetary File System (IPFS)-based storage. Our architecture provides secure and cost-effective data storage and an incentive mechanism. Our experiment shows that as the dataset gets bigger, the Naïve Bayes (NB) and the Support Vector Machine (SVM) models get 2% more accurate, the Convolutional Neural Network (CNN) model gets 4% more accurate, and the Long Short-Term Memory (LSTM) model gets 3 % more accurate. The deep learning models exhibited higher accuracy rates than the machine learning models because hidden layers of deep learning possess the ability to extract intricate syntactic features from the review text.