Abstract
In this paper, we study the problem of personalized text-based music retrieval which takes users' music preferences on songs into account via the analysis of online listening behaviours and social tags. Towards the goal, a novel Dual-Layer Music Preference Topic Model (DL-MPTM) is proposed to construct latent music interest space and characterize the correlations among (user, song, term). Based on the DL-MPTM, we further develop an effective personalized music retrieval system. To evaluate the system's performance, extensive experimental studies have been conducted over two test collections to compare the proposed method with the state-of-the-art music retrieval methods. The results demonstrate that our proposed method significantly outperforms those approaches in terms of personalized search accuracy.
Original language | English |
---|---|
Title of host publication | SIGIR 2016 - Proceedings of the 39th International ACM SIGIR Conference on Research and Development in Information Retrieval |
Place of Publication | Pisa; Italy |
Publisher | Association for Computing Machinery, Inc |
Pages | 125-134 |
Number of pages | 10 |
ISBN (Electronic) | 9781450342902 |
DOIs | |
Publication status | Published - 7 Jul 2016 |
Externally published | Yes |
Event | 39th International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2016 - Pisa, Italy Duration: 17 Jul 2016 → 21 Jul 2016 |
Conference
Conference | 39th International ACM SIGIR Conference on Research and Development in Information Retrieval, SIGIR 2016 |
---|---|
Country/Territory | Italy |
City | Pisa |
Period | 17/07/16 → 21/07/16 |