Affecticon: Emotion-based icons for music retrieval

Min Joon Yoo, In Kwon Lee

Research output: Contribution to journalArticlepeer-review

9 Citations (Scopus)


Affecticon is an efficient system for managing music collections, which groups pieces of music that convey similar emotions and labels each group with a corresponding icon. While developing the system, music samples from Western (US) and Eastern popular songs were used and selected according to the set of samples that wrere distributed uniformly across the AV plane and the sample that express a certain dominant emotion. For each song, 55 features were extracted from the audio signal that correspond to emotion, and to generate the icons, a harmonograph was simulated. Affecticon's interface resembled a standard file explorer system, with affective music icon replacing generic used for a file. Two playlist of each music collections containing well-known songs with which most participants would be familiar were prepared.

Original languageEnglish
Article number5754299
Pages (from-to)89-95
Number of pages7
JournalIEEE Computer Graphics and Applications
Issue number3
Publication statusPublished - 2011

Bibliographical note

Funding Information:
This work was supported by the Industrial Strategic Technology Development Program (grant 10035538, Developing a Tool Converting a Video to Nonphoto-realistic Animations), funded by the Korean Ministry of Knowledge Economy and Mid-career Researcher Program through National Research Foundation grant 20100000389, funded by the Korean Ministry of Education, Science, and Technology.

All Science Journal Classification (ASJC) codes

  • Software
  • Computer Graphics and Computer-Aided Design


Dive into the research topics of 'Affecticon: Emotion-based icons for music retrieval'. Together they form a unique fingerprint.

Cite this