logo SBA

ETD

Archivio digitale delle tesi discusse presso l’Università di Pisa

Tesi etd-09132017-124012


Tipo di tesi
Tesi di laurea magistrale
Autore
CAMPAGNA, MASSIMILIANO
URN
etd-09132017-124012
Titolo
Predicting and explaining the popularity of songs with data mining
Dipartimento
INFORMATICA
Corso di studi
INFORMATICA PER L'ECONOMIA E PER L'AZIENDA (BUSINESS INFORMATICS)
Relatori
relatore Prof.ssa Monreale, Anna
correlatore Dott. Pappalardo, Luca
Parole chiave
  • music data mining
  • songs popularity
Data inizio appello
06/10/2017
Consultabilità
Completa
Riassunto
Data mining techniques recently were used to solve several problems related to
music. This dissertation studies songs popularity in order to find out factors that
make a song popular or not. The outcomes obtained are also used to give an answer
to the myth of four chords. This myth in fact asserts that all popular songs can be
played by using only four chords.
The entire project covers all the stages of Knowledge Discovery in the Databases
process. We aimed to make a first research on songs popularity. In particular, data
on music songs are collected and studied. These data are also used to create several
models using data mining techniques. The problem of predicting and explaining songs
popularity is studied by using both regression and classification algorithms. Finally,
the fittest model is interpreted and tested with specific instances in order to achieve
the goal.
File