Sentiment Analysis of Music using Statistics and Machine Learning
About this ebook
Online streaming platforms have become one of the most important forms of music consumption. Most streaming platforms provide tools to assess the popularity of a song in the forms of scores and rankings. In this book, we address two issues related to song popularity. First, we predict whether an already popular song may attract higher-than-average public interest and become viral. Second, we predict whether sudden spikes in the public interest will translate into long-term popularity growth. We base our findings on data from the streaming platform Billboard, Spotify, and consider appearances in its "Most-Popular" list as indicative of popularity, and appearances in its "Virals" list as indicative of interest growth. We approach the problem as a classification task and employ a Support Vector Machine model built on popularity information to predict interest, and vice versa.
About the author
Aakash Mukherjee has completed his Integrated M.Sc. in Mathematics & Computing from Department of Mathematics, Birla Institute of Technology, Mesra, Ranchi, Jharkhand. His research interests are machine learning, applied and computational statistics. The present work is a part of his master’s dissertation which he completed under the guidance of Prof. Soubhik Chakraborty. Aakash Mukherjee is currently working as Data Scientist at Sumeru Inc.
A PhD in Statistics, Dr. Soubhik Chakraborty is currently a Professor and ex-Head in the Department of Mathematics, Birla Institute of Technology, Mesra, Ranchi, Jharkhand. His research interests are algorithm analysis and music analysis involving extensive use of computational statistics. He has been guiding several research scholars in these areas leading to PhD and has published over 100 papers, 6 books and 9 research monographs. He is also an acknowledged reviewer associated with ACM, IEEE and AMS. He has received several awards
in both teaching and research.
