| KEYWORD |
Evaluating similarity among music artists by means of social media profiling
Parole chiave AUDIO PROCESSING, MACHINE LEARNING, MUSIC, SOCIAL MEDIA
Riferimenti CRISTINA EMMA MARGHERITA ROTTONDI
Gruppi di ricerca Telecommunication Networks Group
Descrizione Artist similarity plays an important role in organizing, understanding, and subsequently, facilitating discovery in large collections of music. Indeed, rules based on artists similarity scores are at the core of the most popular music recommendation systems.
It is arguable that similar artists also share analogies in their social media interactions (e.g., intersections in their set of followers, similar communication style, common types of content etc.). This project aims at validating such argument by comparing the output of a state-of-the-art Machine Learning-based algorithm for the quantification of artist similarity, based on their corpus of musical pieces, to that of state-of-the-art methods for the evaluation of similarity among the artists’ social networks profiles.
The thesis student will be co-tutored by Dr. Massimiliano Zanoni (Politecnico di Milano and Coesioni)
Conoscenze richieste good programming skills, notions of machine learning
Scadenza validita proposta 25/08/2024
PROPONI LA TUA CANDIDATURA