學術產出-Proceedings

Article View/Open

Publication Export

Google ScholarTM

政大圖書館

Citation Infomation

題名 Using emotional context from article for contextual music recommendation
作者 Chen, Chih-Ming;Tsai, Ming-Feng;Liu, J.-Y.;Yang, Y.-H.
陳志明;蔡銘峰
貢獻者 資科系
關鍵詞 Content-based approach; Context information; Context-aware approaches; Factorization machines; Listening context; Music recommendation; Perceptual dimensions; Quality of recommendations
日期 2013-10
上傳時間 28-May-2015 16:59:41 (UTC+8)
摘要 This paper proposes a context-aware approach that recommends music to a user based on the user`s emotional state predicted from the article the user writes. We analyze the association between user-generated text and music by using a real-world dataset with <user, text, music> tripartite information collected from the social blogging website LiveJournal. The audio information represents various perceptual dimensions of music listening, including danceability, loudness, mode, and tempo; the emotional text information consists of bag-of-words and three dimensional affective states within an article: valence, arousal and dominance. To combine these factors for music recommendation, a factorization machine- based approach is taken. Our evaluation shows that the emotional context information mined from user-generated articles does improve the quality of recommendation, com- paring to either the collaborative filtering approach or the content-based approach. Copyright © 2013 ACM.
關聯 MM 2013 - Proceedings of the 2013 ACM Multimedia Conference, 2013, 649-652, 21st ACM International Conference on Multimedia, MM 2013; Barcelona; Spain; 21 October 2013 到 25 October 2013; 類別編號433137; 代碼 100792
資料類型 conference
DOI http://dx.doi.org/10.1145/2502081.2502170
dc.contributor 資科系-
dc.creator (作者) Chen, Chih-Ming;Tsai, Ming-Feng;Liu, J.-Y.;Yang, Y.-H.-
dc.creator (作者) 陳志明;蔡銘峰-
dc.date (日期) 2013-10-
dc.date.accessioned 28-May-2015 16:59:41 (UTC+8)-
dc.date.available 28-May-2015 16:59:41 (UTC+8)-
dc.date.issued (上傳時間) 28-May-2015 16:59:41 (UTC+8)-
dc.identifier.uri (URI) http://nccur.lib.nccu.edu.tw/handle/140.119/75348-
dc.description.abstract (摘要) This paper proposes a context-aware approach that recommends music to a user based on the user`s emotional state predicted from the article the user writes. We analyze the association between user-generated text and music by using a real-world dataset with <user, text, music> tripartite information collected from the social blogging website LiveJournal. The audio information represents various perceptual dimensions of music listening, including danceability, loudness, mode, and tempo; the emotional text information consists of bag-of-words and three dimensional affective states within an article: valence, arousal and dominance. To combine these factors for music recommendation, a factorization machine- based approach is taken. Our evaluation shows that the emotional context information mined from user-generated articles does improve the quality of recommendation, com- paring to either the collaborative filtering approach or the content-based approach. Copyright © 2013 ACM.-
dc.format.extent 176 bytes-
dc.format.mimetype text/html-
dc.relation (關聯) MM 2013 - Proceedings of the 2013 ACM Multimedia Conference, 2013, 649-652, 21st ACM International Conference on Multimedia, MM 2013; Barcelona; Spain; 21 October 2013 到 25 October 2013; 類別編號433137; 代碼 100792-
dc.subject (關鍵詞) Content-based approach; Context information; Context-aware approaches; Factorization machines; Listening context; Music recommendation; Perceptual dimensions; Quality of recommendations-
dc.title (題名) Using emotional context from article for contextual music recommendation-
dc.type (資料類型) conferenceen
dc.identifier.doi (DOI) 10.1145/2502081.2502170-
dc.doi.uri (DOI) http://dx.doi.org/10.1145/2502081.2502170-