Heterogeneous Knowledge-Based Attentive Neural Networks for Short-Term Music Recommendations
The current existing data in online music service platforms are heterogeneous, extensive, and disorganized. Finding an effective method to use these data in recommending appropriate music to users during a short-term session is a significant challenge. Another serious problem is that most of the dat...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2018-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/8486952/ |
id |
doaj-8971fcb1a9384a908256967c7a9d0e30 |
---|---|
record_format |
Article |
spelling |
doaj-8971fcb1a9384a908256967c7a9d0e302021-03-29T21:40:29ZengIEEEIEEE Access2169-35362018-01-016589905900010.1109/ACCESS.2018.28749598486952Heterogeneous Knowledge-Based Attentive Neural Networks for Short-Term Music RecommendationsQika Lin0https://orcid.org/0000-0001-5650-0600Yaoqiang Niu1Yifan Zhu2https://orcid.org/0000-0002-7695-1633Hao Lu3https://orcid.org/0000-0002-8065-8499Keith Zvikomborero Mushonga4Zhendong Niu5School of Computer Science and Technology, Beijing Institute of Technology, Beijing, ChinaSchool of Computer Technology, Lanzhou Jiaotong University, Lanzhou, ChinaSchool of Computer Science and Technology, Beijing Institute of Technology, Beijing, ChinaSchool of Computer Science and Technology, Beijing Institute of Technology, Beijing, ChinaSchool of Computer Science and Technology, Beijing Institute of Technology, Beijing, ChinaSchool of Computer Science and Technology, Beijing Institute of Technology, Beijing, ChinaThe current existing data in online music service platforms are heterogeneous, extensive, and disorganized. Finding an effective method to use these data in recommending appropriate music to users during a short-term session is a significant challenge. Another serious problem is that most of the data, in reality, obey the long-tailed distribution, which consequently leads to traditional music recommendation systems recommending a lot of popular music that users do not like on a specific occasion. To solve these problems, we propose a heterogeneous knowledge-based attentive neural network model for short-term music recommendations. First, we collect three types of data for modeling entities in user–music interaction network, i.e., graphic, textual, and visual data, and then embed them into high-dimensional spaces using the TransR, distributed memory version of paragraph vector, and variational autoencoder methods, respectively. The concatenation of these embedding results is an abstract representation of the entity. Based on this, a recurrent neural network with an attention mechanism is built, which is capable of obtaining users’ preferences in the current session and consequently making recommendations. The experimental results show that our proposed approach outperforms the current state-of-the-art short-term music recommendation systems on one real-world dataset. In addition, it can also recommend more relatively unpopular songs compared with classic models.https://ieeexplore.ieee.org/document/8486952/Heterogeneous knowledgedata embeddingentity representationattentive neural networksshort-term music recommendation |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Qika Lin Yaoqiang Niu Yifan Zhu Hao Lu Keith Zvikomborero Mushonga Zhendong Niu |
spellingShingle |
Qika Lin Yaoqiang Niu Yifan Zhu Hao Lu Keith Zvikomborero Mushonga Zhendong Niu Heterogeneous Knowledge-Based Attentive Neural Networks for Short-Term Music Recommendations IEEE Access Heterogeneous knowledge data embedding entity representation attentive neural networks short-term music recommendation |
author_facet |
Qika Lin Yaoqiang Niu Yifan Zhu Hao Lu Keith Zvikomborero Mushonga Zhendong Niu |
author_sort |
Qika Lin |
title |
Heterogeneous Knowledge-Based Attentive Neural Networks for Short-Term Music Recommendations |
title_short |
Heterogeneous Knowledge-Based Attentive Neural Networks for Short-Term Music Recommendations |
title_full |
Heterogeneous Knowledge-Based Attentive Neural Networks for Short-Term Music Recommendations |
title_fullStr |
Heterogeneous Knowledge-Based Attentive Neural Networks for Short-Term Music Recommendations |
title_full_unstemmed |
Heterogeneous Knowledge-Based Attentive Neural Networks for Short-Term Music Recommendations |
title_sort |
heterogeneous knowledge-based attentive neural networks for short-term music recommendations |
publisher |
IEEE |
series |
IEEE Access |
issn |
2169-3536 |
publishDate |
2018-01-01 |
description |
The current existing data in online music service platforms are heterogeneous, extensive, and disorganized. Finding an effective method to use these data in recommending appropriate music to users during a short-term session is a significant challenge. Another serious problem is that most of the data, in reality, obey the long-tailed distribution, which consequently leads to traditional music recommendation systems recommending a lot of popular music that users do not like on a specific occasion. To solve these problems, we propose a heterogeneous knowledge-based attentive neural network model for short-term music recommendations. First, we collect three types of data for modeling entities in user–music interaction network, i.e., graphic, textual, and visual data, and then embed them into high-dimensional spaces using the TransR, distributed memory version of paragraph vector, and variational autoencoder methods, respectively. The concatenation of these embedding results is an abstract representation of the entity. Based on this, a recurrent neural network with an attention mechanism is built, which is capable of obtaining users’ preferences in the current session and consequently making recommendations. The experimental results show that our proposed approach outperforms the current state-of-the-art short-term music recommendation systems on one real-world dataset. In addition, it can also recommend more relatively unpopular songs compared with classic models. |
topic |
Heterogeneous knowledge data embedding entity representation attentive neural networks short-term music recommendation |
url |
https://ieeexplore.ieee.org/document/8486952/ |
work_keys_str_mv |
AT qikalin heterogeneousknowledgebasedattentiveneuralnetworksforshorttermmusicrecommendations AT yaoqiangniu heterogeneousknowledgebasedattentiveneuralnetworksforshorttermmusicrecommendations AT yifanzhu heterogeneousknowledgebasedattentiveneuralnetworksforshorttermmusicrecommendations AT haolu heterogeneousknowledgebasedattentiveneuralnetworksforshorttermmusicrecommendations AT keithzvikomboreromushonga heterogeneousknowledgebasedattentiveneuralnetworksforshorttermmusicrecommendations AT zhendongniu heterogeneousknowledgebasedattentiveneuralnetworksforshorttermmusicrecommendations |
_version_ |
1724192528578641920 |