透過您的圖書館登入
IP:3.138.122.4
  • 學位論文

基於使用者動態聽歌興趣之音樂推薦方法

Music Recommendation based on Dynamic User Interests

指導教授 : 鄭卜壬

摘要


此篇論文中,我們提出了一種在線上音樂播放中使用的動態權重機 制。基於隱性因子模型之假設,使用者、歌曲、歌手皆是由一組隱性 空間中的向量表示。給定一使用者以及他的近期播放紀錄,即可判斷 他目前的興趣是傾向近期偏好或是長期偏好。同其他隱性因子模型, 此機制可在不使用內容資料的情形下訓練。這在使用網路播放紀錄當 做資料庫時是一個利基,因內容資料相對較難取得。在數個 last.fm 資 料集上的實驗結果顯示此方法確實有效。 關鍵字:音樂推薦,動態興趣,隱性因子向量模型,機器學習,梯度 上升

並列摘要


In this paper, we propose a dynamic weight tuning scheme for online mu- sic recommendation. Based on a latent factor model, songs, artists, and users are mapped into a latent space. Then, given each user’s recent songs we can determine his current interest for music, which either similar to his past be- havior or more like recent ones. Like latent factor based models, this scheme can be trained without content information, which is a benefit when adopting internet radios as data source. Experimental results on the last.fm collections show that our proposed method is effective. Keywords: Music Recommendation, Dynamic Interests, Latent Factor Model, Machine Learning, Gradient Ascent

參考文獻


chroma-based representations. Multimedia, IEEE Transactions on, 7(1):96–104,
mantic audio content-based music recommendation and visualization based on user
dation by unified hypergraph: combining social media information and music con-
ACM, 2010.
[6] O. Celma. Music Recommendation and Discovery in the Long Tail. Springer, 2010.

延伸閱讀