A Survey on Various Aspects of Recommendation System Based on Sentiment Analysis

Many industries, including e-commerce, media, finance, and utilities, have embraced recommender systems. To maximize customer happiness, this type of technology uses a vast quantity of data. These recommendations assist customers in selecting items, while companies can enhance product use. When it comes to analyzing social data, sentiment analysis may be used to acquire a better knowledge of users’ thoughts and feelings, which is useful for enhancing the dependability of recommendation systems. However, this data may also be utilized to supplement user ratings of items. According to some, sentiment analysis (SA) of articles that may be found in online news sources and blogs or even in the recommender systems themselves can provide better recommendations to users. Research trends that connect sophisticated technological components of recommendation systems utilized in many service domains with the commercial aspects of these services are reviewed in this article. We must first conduct an accurate evaluation of recommendations models for recommendation systems (RS) using data mining and application service research. Deep learning architectures for breast cancer detection are the topic of this review. The following is a list of current machine learning-based technologies that will be discussed in this survey. Research into recommendation systems is made possible by this study’s examination of the numerous technologies and service trends to which recommendation systems may be applied, which gives a complete overview of the area.