Recommendation systems (RSs) are widely used in e-commerce to improve conversion rates by aligning product offerings with customer preferences and interests. While traditional RSs rely solely on numerical ratings to generate recommendations, these ratings alone may not be sufficient to offer personalized and accurate suggestions. To overcome this limitation, additional sources of information, such as reviews, can be utilized. However, analyzing and understanding the information contained within reviews, which are often unstructured data, is a challenging task. To address this issue, sentiment analysis (SA) has attracted considerable attention as a tool to better comprehend a user’s opinions, emotions, and attitudes. In this study, we propose a novel RS that leverages ensemble learning by integrating sentiment analysis of textual data with collaborative filtering techniques to provide users with more precise and individualized recommendations. Our system was developed in three main steps. Firstly, we used unsupervised “GloVe” vectorization for better classification performance and built a sentiment model based on Bidirectional Long Short-Term Memory (Bi-LSTM). Secondly, we developed a recommendation model based on collaborative filtering techniques. Lastly, we integrated our sentiment analysis model into the RS. Our proposed model of SA achieved an accuracy score of 93%, which is superior to other models. The results of our study indicate that our approach enhances the accuracy of the recommendation system. Overall, our proposed system offers customers a more reliable and personalized recommendation service in e-commerce.

The enhancement of e-commerce conversion rates heavily relies on personalized product recommendations generated by recommendation systems (RS). Despite successful techniques, challenges like sparse data and cold-start issues hinder their effectiveness. To tackle these obstacles, leveraging additional information sources like user and item profiles becomes crucial. This study focuses on a sophisticated RS architecture that combines Neural Collaborative Filtering (NCF) with Global vectors for word representation (GloVe) and Deep Neural Network (DNN), to address sparsity and cold-start problems. By integrating GloVe-DNN, a deeper understanding of item profiles is achieved, enabling a better grasp of user preferences and item traits. This detailed understanding, alongside the Neural Collaborative Filtering model, enables the system to offer highly personalized suggestions. The proposed method involves four main stages: creating the GloVe Embedding model to generate embeddings from item profile text, utilizing these vectors to build a Deep Neural Network, implementing the NCF method, and finally, developing an ensemble learning technique that combines these approaches, followed by a thorough evaluation. Empirical results strongly confirm the effectiveness of our approach, especially the fusion of GloVe-DNN with Neural CF techniques, demonstrating significant improvements across various performance measures.