A Scientometric Analysis to Study Research Trends in Music Recommendation System using Collaborative Filtering and Semantic Analysis

The primary goal of this paper is to carry out a thorough scientometric study of scholarly articles concerning to the Personalized Music Recommendation System, with a focus on semantic analysis and collaborative filtering techniques. Recommendation systems have grown in popularity and are now an integral part of consumer-based programmes such as shopping, music, and movies. To improve understanding of customer needs, new algorithms are being developed. Recommendation programmes have recently acquired the entertainment and e-commerce industries by storm. Amazon, Netflix, and Spotify are good examples of platforms where the recommendation system perform a significant role in their popularity. The scientometric analysis was performed on the results obtained from the Scopus repository over the last fifteen years by examining frequently used keywords, the amount of work done in different countries, the annual research development, prolific authors, and the frequency of article citations, among other things. Graphs and charts are created using tools like Word Cloud and BiblioShiny. This paper provides an accurate picture of the amount of work done in various countries as well as the year-by-year progression of research in the music recommendation system domain. This scientometric analysis will assist beginners in conducting a literature survey using appropriate literature from the Scopus database.