DocumentCode
3692703
Title
Evaluating text features for lyrics-based songwriter prediction
Author
Başar Kırmacı;Hasan Oğul
Author_Institution
Department of Computer Engineering, Baş
fYear
2015
Firstpage
405
Lastpage
409
Abstract
We offer an automated way of estimating the author of a song using only its lyrics content. To this end, we introduce a complete text classification framework which takes raw lyrics data as input and report estimated songwriter. The performance of the system is evaluated based on its classification and retrieval ability on a large dataset of Turkish songs, which was collected in this study. The results promote the use of such technique as a complementary tool in music information retrieval applications.
Keywords
"Support vector machines","Text categorization","Music information retrieval","Kernel","Feature extraction","Accuracy","Computational modeling"
Publisher
ieee
Conference_Titel
Intelligent Engineering Systems (INES), 2015 IEEE 19th International Conference on
Type
conf
DOI
10.1109/INES.2015.7329743
Filename
7329743
Link To Document