UNIVERSITAS BINA DARMA, UNIVERSITAS BINA DARMA (2022) Music Retrieval using Mood Tags in Folksonomy Chang Bae Moon, HyunSoo Kim, Dong-Seong Kim, Sung-Phil Heo, Byeong Man Kim. Music Retrieval using Mood Tags in Folksonomy Chang Bae Moon, HyunSoo Kim, Dong-Seong Kim, Sung-Phil Heo, Byeong Man Kim.
|
Text
1. Music Retrieval using Mood Tags in Folksonomy.pdf Download (245kB) | Preview |
Abstract
This paper propose a music retrieval using mood tats in folksonomy for solving Syn�onym problems. Normally, a music piece and a mood tag can be represented by mood numeric vectors internally. To determine the mood vectors of a music piece, 12 re�gressors are created by Support Vector Regression using features of a music piece. Then, a mood vector is predicted by the 12 regressors. To map a folksonomy mood tags to its mood numeric vectors, the relationship between mood vectors of music piece and the folksonomy mood tags was investigated based on tagging data retrieved from Last.fm. To evaluate retrieval performance, music pieces on Last.fm anno�tated with at least one mood tag were used as a test set. When calculating precision and recall, music pieces annotated with synonyms of a given query tag were treated as relevant. These experiments on a real-world data set illustrate the utility of the internal tagging of music. Our approach offers a practical solution to the problem caused by synonyms.
| Item Type: | Article |
|---|---|
| Subjects: | H Social Sciences > H Social Sciences (General) |
| Divisions: | Faculty of Law, Arts and Social Sciences > School of Art |
| Depositing User: | Mr Edi Surya Negara |
| Date Deposited: | 05 Jul 2022 04:29 |
| Last Modified: | 05 Jul 2022 04:29 |
| URI: | http://eprints.binadarma.ac.id/id/eprint/16968 |
Actions (login required)
 |
View Item |
