File Download
There are no files associated with this item.
Links for fulltext
(May Require Subscription)
- Publisher Website: 10.1145/3383583.3398623
- Scopus: eid_2-s2.0-85095120687
Supplementary
-
Citations:
- Scopus: 0
- Appears in Collections:
Conference Paper: A Multimodal Music Recommendation System with Listeners' Personality and Physiological Signals
Title | A Multimodal Music Recommendation System with Listeners' Personality and Physiological Signals |
---|---|
Authors | |
Issue Date | 2020 |
Publisher | Association for Computing Machinery (ACM). The Proceedings' web site is located at https://dl.acm.org/conference/jcdl |
Citation | Proceedings of the ACM/IEEE Joint Conference on Digital Libraries in 2020 (JCDL '20), Virtual Event, China, 1-5 August 2020, p. 357-360 How to Cite? |
Abstract | This preliminary study explored multiple information sources for music recommendation system (MRS), including users' personality traits measured by the Ten-Item Personality Inventory (TIPI) and physiological signals recorded by a wearable wristband. A dataset of 23 participants and 628 song listening records were obtained from a user experiment, with matched personality, physiological signals as well as music acoustic features. Based on the dataset, a machine learning experiment with four regression algorithms was conducted to compare recommendation performances across different combinations of feature sets. Results show that personality features contributed significantly to the improvement of recommender accuracy, while physiological features contributed less. Analysis of top features in the best performing model revealed the importance of some physiological features. Future studies are called for to further investigate multimodal MRS through exploiting user properties and context data. |
Persistent Identifier | http://hdl.handle.net/10722/305577 |
ISBN |
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Liu, R | - |
dc.contributor.author | Hu, X | - |
dc.date.accessioned | 2021-10-20T10:11:22Z | - |
dc.date.available | 2021-10-20T10:11:22Z | - |
dc.date.issued | 2020 | - |
dc.identifier.citation | Proceedings of the ACM/IEEE Joint Conference on Digital Libraries in 2020 (JCDL '20), Virtual Event, China, 1-5 August 2020, p. 357-360 | - |
dc.identifier.isbn | 9781450375856 | - |
dc.identifier.uri | http://hdl.handle.net/10722/305577 | - |
dc.description.abstract | This preliminary study explored multiple information sources for music recommendation system (MRS), including users' personality traits measured by the Ten-Item Personality Inventory (TIPI) and physiological signals recorded by a wearable wristband. A dataset of 23 participants and 628 song listening records were obtained from a user experiment, with matched personality, physiological signals as well as music acoustic features. Based on the dataset, a machine learning experiment with four regression algorithms was conducted to compare recommendation performances across different combinations of feature sets. Results show that personality features contributed significantly to the improvement of recommender accuracy, while physiological features contributed less. Analysis of top features in the best performing model revealed the importance of some physiological features. Future studies are called for to further investigate multimodal MRS through exploiting user properties and context data. | - |
dc.language | eng | - |
dc.publisher | Association for Computing Machinery (ACM). The Proceedings' web site is located at https://dl.acm.org/conference/jcdl | - |
dc.relation.ispartof | Proceedings of the ACM/IEEE Joint Conference on Digital Libraries in 2020 | - |
dc.title | A Multimodal Music Recommendation System with Listeners' Personality and Physiological Signals | - |
dc.type | Conference_Paper | - |
dc.identifier.email | Hu, X: xiaoxhu@hku.hk | - |
dc.identifier.authority | Hu, X=rp01711 | - |
dc.description.nature | link_to_subscribed_fulltext | - |
dc.identifier.doi | 10.1145/3383583.3398623 | - |
dc.identifier.scopus | eid_2-s2.0-85095120687 | - |
dc.identifier.hkuros | 327874 | - |
dc.identifier.spage | 357 | - |
dc.identifier.epage | 360 | - |
dc.publisher.place | New York, NY | - |