學術產出-Periodical Articles

Article View/Open

Publication Export

Google ScholarTM

政大圖書館

Citation Infomation

題名 A Music Recommendation System Based on Music and User Grouping
作者 陳良弼
Chen,Hung-Chen;Chen,Arbee L. P.
貢獻者 資科系
關鍵詞 access histories; music recommendation; perceptual properties; recommendation methods; user profiles
日期 2005
上傳時間 21-Aug-2014 15:00:24 (UTC+8)
摘要 In this paper, we present a music recommendation system, which provides a personalized service of music recommendation. The polyphonic music objects of MIDI format are first analyzed for deriving information for music grouping. For this purpose, the representative track of each polyphonic music object is first determined, and then six features are extracted from this track for proper music grouping. Moreover, the user access histories are analyzed to derive the profiles of user interests and behaviors for user grouping. The content-based, collaborative, and statistics-based recommendation methods are proposed based on the favorite degrees of the users to the music groups, and the user groups they belong to. A series of experiments are carried out to show that our approach performs well.
關聯 Journal of Intelligent Information Systems,24:2/3,113-132
資料類型 article
DOI http://dx.doi.org/10.1007/s10844-005-0319-3
dc.contributor 資科系en_US
dc.creator (作者) 陳良弼zh_TW
dc.creator (作者) Chen,Hung-Chen;Chen,Arbee L. P.en_US
dc.date (日期) 2005en_US
dc.date.accessioned 21-Aug-2014 15:00:24 (UTC+8)-
dc.date.available 21-Aug-2014 15:00:24 (UTC+8)-
dc.date.issued (上傳時間) 21-Aug-2014 15:00:24 (UTC+8)-
dc.identifier.uri (URI) http://nccur.lib.nccu.edu.tw/handle/140.119/69139-
dc.description.abstract (摘要) In this paper, we present a music recommendation system, which provides a personalized service of music recommendation. The polyphonic music objects of MIDI format are first analyzed for deriving information for music grouping. For this purpose, the representative track of each polyphonic music object is first determined, and then six features are extracted from this track for proper music grouping. Moreover, the user access histories are analyzed to derive the profiles of user interests and behaviors for user grouping. The content-based, collaborative, and statistics-based recommendation methods are proposed based on the favorite degrees of the users to the music groups, and the user groups they belong to. A series of experiments are carried out to show that our approach performs well.en_US
dc.format.extent 332646 bytes-
dc.format.mimetype application/pdf-
dc.language.iso en_US-
dc.relation (關聯) Journal of Intelligent Information Systems,24:2/3,113-132en_US
dc.subject (關鍵詞) access histories; music recommendation; perceptual properties; recommendation methods; user profilesen_US
dc.title (題名) A Music Recommendation System Based on Music and User Groupingen_US
dc.type (資料類型) articleen
dc.identifier.doi (DOI) 10.1007/s10844-005-0319-3en_US
dc.doi.uri (DOI) http://dx.doi.org/10.1007/s10844-005-0319-3en_US