| dc.contributor | 資科系 | |
| dc.creator (作者) | 陳志明 | zh_TW |
| dc.creator (作者) | 蔡銘峰 | zh_TW |
| dc.creator (作者) | Chen, Chih Ming | en_US |
| dc.creator (作者) | Tsai, Ming Feng | en_US |
| dc.creator (作者) | Lin, Yu Ching | en_US |
| dc.creator (作者) | Yang, Yi-Hsuan | en_US |
| dc.date (日期) | 2016-09 | |
| dc.date.accessioned | 31-Aug-2017 14:51:58 (UTC+8) | - |
| dc.date.available | 31-Aug-2017 14:51:58 (UTC+8) | - |
| dc.date.issued (上傳時間) | 31-Aug-2017 14:51:58 (UTC+8) | - |
| dc.identifier.uri (URI) | http://nccur.lib.nccu.edu.tw/handle/140.119/112470 | - |
| dc.description.abstract (摘要) | A common scenario considered in recommender systems is to predict a user`s preferences on unseen items based on his/her preferences on observed items. A major limitation of this scenario is that a user might be interested in different things each time when using the system, but there is no way to allow the user to actively alter or adjust the recommended results. To address this issue, we propose the idea of "query-based recommendation" that allows a user to specify his/her search intention while exploring new items, thereby incorporating the concept of information retrieval into recommendation systems. Moreover, the idea is more desirable when the user intention can be expressed in different ways. Take music recommendation as an example: the proposed system allows a user to explore new song tracks by specifying either a track, an album, or an artist. To enable such heterogeneous queries in a recommender system, we present a novel technique called "Heterogeneous Preference Embedding" to encode user preference and query intention into low-dimensional vector spaces. Then, with simple search methods or similarity calculations, we can use the encoded representation of queries to generate recommendations. This method is fairly exible and it is easy to add other types of information when available. Evaluations on three music listening datasets confirm the effectiveness of the proposed method over the state-of-the-art matrix factorization and network embedding methods. | |
| dc.format.extent | 575201 bytes | - |
| dc.format.mimetype | application/pdf | - |
| dc.relation (關聯) | RecSys 2016 - Proceedings of the 10th ACM Conference on Recommender Systems, 79-82 | en_US |
| dc.subject (關鍵詞) | Factorization; Recommender systems; Vector spaces; Heterogeneous preference embedding; Matrix factorizations; Music recommendation; Network embedding; Query-based recommendation; Search intentions; Similarity calculation; User`s preferences; Search engines | |
| dc.title (題名) | Query-based music recommendations via preference embedding | en_US |
| dc.type (資料類型) | conference | |
| dc.identifier.doi (DOI) | 10.1145/2959100.2959169 | |
| dc.doi.uri (DOI) | http://dx.doi.org/10.1145/2959100.2959169 | |
