Joint Deep Network With Auxiliary Semantic Learning for Popular Recommendation
There is a cold-start problem in the recommendation system field, which is how to profile new users and new items. The popular recommendation algorithm is an important solution to the cold-start problem. In this paper, we propose a new joint deep network model with auxiliary semantic learning for th...
Main Authors: | , , |
---|---|
Format: | Article |
Language: | English |
Published: |
IEEE
2020-01-01
|
Series: | IEEE Access |
Subjects: | |
Online Access: | https://ieeexplore.ieee.org/document/9016006/ |
id |
doaj-04366676495649948358d86c0b1d68c3 |
---|---|
record_format |
Article |
spelling |
doaj-04366676495649948358d86c0b1d68c32021-03-30T02:04:35ZengIEEEIEEE Access2169-35362020-01-018412544126110.1109/ACCESS.2020.29764989016006Joint Deep Network With Auxiliary Semantic Learning for Popular RecommendationXingkai Wang0https://orcid.org/0000-0001-6205-5451Yiqiang Sheng1https://orcid.org/0000-0002-8452-2492Haojiang Deng2National Network New Media Engineering Research Center, Institute of Acoustics, Chinese Academy of Sciences, Beijing, ChinaNational Network New Media Engineering Research Center, Institute of Acoustics, Chinese Academy of Sciences, Beijing, ChinaNational Network New Media Engineering Research Center, Institute of Acoustics, Chinese Academy of Sciences, Beijing, ChinaThere is a cold-start problem in the recommendation system field, which is how to profile new users and new items. The popular recommendation algorithm is an important solution to the cold-start problem. In this paper, we propose a new joint deep network model with auxiliary semantic learning for the popular recommendation algorithm (DMPRA). First, we define the items with a large quantity of review data and high ratings as the popular recommended items. Second, we introduce text analysis into the popular recommendation algorithm. We use the optimized CharCNN networks to learn the auxiliary semantic vectors from the users' reviews. Then, we use the Factorization Machine (FM) component and deep component to learn the corresponding vector representations of the items' attribute features. We use convolution to simulate the interaction of hidden latent vectors. This method can make the vectors interact more satisfactorily than traditional interactive representation methods. Finally, we provide the users with a reasonable popular recommendation list. The experimental results show that our algorithm can improve the AUC (area under the ROC curve) and Logloss (cross-entropy) of the popular items' prediction. In addition, we provide relevant explanations for some useful phenomena.https://ieeexplore.ieee.org/document/9016006/Popular recommendation algorithmjoint deep networksemantic learning |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Xingkai Wang Yiqiang Sheng Haojiang Deng |
spellingShingle |
Xingkai Wang Yiqiang Sheng Haojiang Deng Joint Deep Network With Auxiliary Semantic Learning for Popular Recommendation IEEE Access Popular recommendation algorithm joint deep network semantic learning |
author_facet |
Xingkai Wang Yiqiang Sheng Haojiang Deng |
author_sort |
Xingkai Wang |
title |
Joint Deep Network With Auxiliary Semantic Learning for Popular Recommendation |
title_short |
Joint Deep Network With Auxiliary Semantic Learning for Popular Recommendation |
title_full |
Joint Deep Network With Auxiliary Semantic Learning for Popular Recommendation |
title_fullStr |
Joint Deep Network With Auxiliary Semantic Learning for Popular Recommendation |
title_full_unstemmed |
Joint Deep Network With Auxiliary Semantic Learning for Popular Recommendation |
title_sort |
joint deep network with auxiliary semantic learning for popular recommendation |
publisher |
IEEE |
series |
IEEE Access |
issn |
2169-3536 |
publishDate |
2020-01-01 |
description |
There is a cold-start problem in the recommendation system field, which is how to profile new users and new items. The popular recommendation algorithm is an important solution to the cold-start problem. In this paper, we propose a new joint deep network model with auxiliary semantic learning for the popular recommendation algorithm (DMPRA). First, we define the items with a large quantity of review data and high ratings as the popular recommended items. Second, we introduce text analysis into the popular recommendation algorithm. We use the optimized CharCNN networks to learn the auxiliary semantic vectors from the users' reviews. Then, we use the Factorization Machine (FM) component and deep component to learn the corresponding vector representations of the items' attribute features. We use convolution to simulate the interaction of hidden latent vectors. This method can make the vectors interact more satisfactorily than traditional interactive representation methods. Finally, we provide the users with a reasonable popular recommendation list. The experimental results show that our algorithm can improve the AUC (area under the ROC curve) and Logloss (cross-entropy) of the popular items' prediction. In addition, we provide relevant explanations for some useful phenomena. |
topic |
Popular recommendation algorithm joint deep network semantic learning |
url |
https://ieeexplore.ieee.org/document/9016006/ |
work_keys_str_mv |
AT xingkaiwang jointdeepnetworkwithauxiliarysemanticlearningforpopularrecommendation AT yiqiangsheng jointdeepnetworkwithauxiliarysemanticlearningforpopularrecommendation AT haojiangdeng jointdeepnetworkwithauxiliarysemanticlearningforpopularrecommendation |
_version_ |
1724185807412002816 |