Customer centric hybrid recommendation system for E-Commerce applications by integrating hybrid sentiment analysis

Internet applications such as Online Social Networking and Electronic commerce are becoming incredibly common, resulting in more content being available. Recommender systems (RS) assist users in identifying appropriate information out of a large pool of options. In today's internet applications, RS are extremely important. To increase user satisfaction, this type of system supports personalized recommendations based on a massive volume of data. These suggestions assist clients in selecting products, while concerns can increase product utilization. We discovered that much research work is going on in the field of recommendation and that there are some effective systems out there. In the context of social information, sentimental analysis (SA) can aid in increasing the knowledge of a user's behaviour, views, and reactions, which is helpful for incorporating into RS to improve recommendation accuracy. RS has been found to resolve information overload challenges in information retrieval, but they still have issues with cold-start and data sparsity. SA, on the other hand, is well-known for interpreting text and conveying user choices. It's frequently used to assist E-Commerce in tracking customer feedback on their products and attempting to comprehend customer needs and preferences. To improve the accuracy and correctness of any RS, this paper proposes a recommendation model based on a Hybrid Recommendation Model (HRM) and hybrid SA. In the proposed method, we first generate a preliminary recommendation list using a HRM. To generate the final recommendation list, the HRM with SA is used. In terms of various evaluation criteria, the HRM with SA outperforms traditional models.

Automated summary

This paper discusses the importance of recommender systems in internet applications and the role of sentimental analysis in improving recommendation accuracy. By proposing a recommendation model based on a hybrid recommendation model and sentimental analysis, the performance of the recommender system can be enhanced.