Presentation 2022-12-21
On the relationship between lyricist-artist entropy and lyricist classification difficulty
Mitsuki Morita, Masato Kikuchi, Tadachika Ozono,
PDF Download Page PDF download Page Link
Abstract(in Japanese) (See Japanese page)
Abstract(in English) Determining a lyricist of a lyric is a more difficult task than an author of a novel. A lyric may contain a mixture of inseparable characteristics of a lyricist, a singer, and topics because some lyricists write songs for singers considering topics. We aim to realize a method to understand and extract the characteristics of lyricists from lyrics. If the characteristics of lyricists are prominent, lyrics can be easily classifiable by lyricists. We investigated whether the lyrist-singer entropy affects classification performance. This investigation suggests how lyricists optimize songwriting for singers. This paper describes our experiments and results.
Keyword(in Japanese) (See Japanese page)
Keyword(in English) lyricist classification / lyricist-artist entropy / lyric analysis / BERT
Paper # AI2022-33
Date of Issue 2022-12-14 (AI)

Conference Information
Committee AI
Conference Date 2022/12/21(1days)
Place (in Japanese) (See Japanese page)
Place (in English)
Topics (in Japanese) (See Japanese page)
Topics (in English)
Chair Yuichi Sei(Univ. of Electro-Comm.)
Vice Chair Yuko Sakurai(AIST) / Tadachika Ozono(Nagoya Inst. of Tech.)
Secretary Yuko Sakurai(Tokyo Univ. of Agriculture and Technology) / Tadachika Ozono(Toho Univ.)
Assistant Kazutaka Matsuzaki(Chuo Univ.)

Paper Information
Registration To Technical Committee on Artificial Intelligence and Knowledge-Based Processing
Language JPN
Title (in Japanese) (See Japanese page)
Sub Title (in Japanese) (See Japanese page)
Title (in English) On the relationship between lyricist-artist entropy and lyricist classification difficulty
Sub Title (in English)
Keyword(1) lyricist classification
Keyword(2) lyricist-artist entropy
Keyword(3) lyric analysis
Keyword(4) BERT
1st Author's Name Mitsuki Morita
1st Author's Affiliation Nagoya Institute of Technology(NITech)
2nd Author's Name Masato Kikuchi
2nd Author's Affiliation Nagoya Institute of Technology(NITech)
3rd Author's Name Tadachika Ozono
3rd Author's Affiliation Nagoya Institute of Technology(NITech)
Date 2022-12-21
Paper # AI2022-33
Volume (vol) vol.122
Number (no) AI-322
Page pp.pp.1-6(AI),
#Pages 6
Date of Issue 2022-12-14 (AI)