基于注意力增强的热点感知新闻推荐模型
HAN:Hotspot-Aware Attention Enhanced News Recommendation
查看参考文献33篇
|
文摘
|
完全个性化的新闻推荐工作通常只基于用户兴趣,可能会导致推荐结果与点击过的内容过于相似甚至重复.事实上即使一些热点新闻并不完全符合用户兴趣,用户也可能希望点击类似的新闻.目前基于热点的新闻推荐方法不能很好挖掘潜在新闻的热点特征、灵活平衡用户兴趣和热点特征.本文提出一种新颖的注意力增强的热点感知新闻推荐模型(Hotspot-aware Attention enhaNced model,HAN),充分利用注意力网络和自注意力网络等深度神经网络的优势,在个性化推荐中将个性化兴趣与新闻热点性进行更好平衡与利用.该模型包括新闻编码器、热点特征提取器、用户兴趣提取器和点击预测器四个组件.提出一个热点特征提取器,使用注意力网络动态聚合热点新闻学习热点表示以更好挖掘热点特征;提出一个新颖的点击预测器来灵活融合热点特征、用户兴趣和候选新闻,以提升候选新闻的点击预测准确率.真实数据集上的实验表明HAN模型在AUC(Area Under the Curve of ROC)和F1两项指标上分别提升了7.51%和8.63%,且能够有效缓解用户冷启动问题. |
|
其他语种文摘
|
Personalized news recommendation is usually based on users' interests only,which may cause the recommendation results to be too similar with or even repeat the content that has been clicked.In fact,even if some hot news may not meet the user's interests,users may also want to click on similar news.At present,hotspot-based approaches usually can not well mine the potential news hotspot features and flexibly balance the user interest and hotspot features.In this paper,a hotspot-aware attention enhanced model (HAN) for news recommendation is proposed,which makes full use of the advantages of deep neural networks such as attention networks and self-attention networks to better balance and utilize personalized interests and news hotspot in recommendation algorithm.HAN includes four components:news encoder,hotspot feature extractor,user interests extractor and click predictor.In order to effectively mine hotspot features,a hotspot feature extractor is proposed,which uses an attention network to dynamically aggregate hot news and learn hotspot feature representation;in order to improve the accuracy of predicting the click probability of candidate news,a click predictor is proposed to flexibly fuse hotspot features,user interests feature and candidate news representation.Experiments on a real-world dataset show that the area under the curve of ROC (AUC) and F1 increase by 7.51% and 8.63% respectively.At the same time,the model also helps to alleviate the cold-start problem of users. |
|
来源
|
电子学报
,2023,51(1):93-104 【核心库】
|
|
DOI
|
10.12263/DZXB.20210570
|
|
关键词
|
新闻推荐
;
热点感知
;
自注意力网络
;
注意力网络
;
卷积神经网络
|
|
地址
|
1.
北京林业大学信息学院, 北京, 100083
2.
国家林业草原林业智能信息处理工程技术研究中心, 国家林业草原林业智能信息处理工程技术研究中心, 北京, 100083
|
|
语种
|
中文 |
|
文献类型
|
研究性论文 |
|
ISSN
|
0372-2112 |
|
学科
|
自动化技术、计算机技术 |
|
基金
|
国家重点研发计划
|
|
文献收藏号
|
CSCD:7419784
|
参考文献 共
33
共2页
|
|
1.
Prawesh S. The" top N" news recommender: Count distortion and manipulation resistance.
Proceedings of the Fifth ACM Conference on Recommender Systems,2011:237-244
|
CSCD被引
1
次
|
|
|
|
|
2.
Gulla J A. 3rd international workshop on news recommendation and analytics (INRA 2015).
Proceedings of the 9th ACM Conference on Recommender Systems,2015:345-346
|
CSCD被引
1
次
|
|
|
|
|
3.
Chen C. Location-aware personalized news recommendation with deep semantic analysis.
IEEE Access,2017,5:1624-1638
|
CSCD被引
9
次
|
|
|
|
|
4.
田萱. 基于深度学习的新闻推荐算法研究综述.
计算机科学与探索,2021,15(6):971-998
|
CSCD被引
10
次
|
|
|
|
|
5.
Wu C H. NPA: Neural news recommendation with personalized attention.
Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining,2019:2576-2584
|
CSCD被引
3
次
|
|
|
|
|
6.
Wu C H.
Neural news recommendation with attentive multi-view learning,2019
|
CSCD被引
2
次
|
|
|
|
|
7.
Wang X K. Joint deep network with auxiliary semantic learning for popular recommendation.
IEEE Access,8:41254-41261
|
CSCD被引
2
次
|
|
|
|
|
8.
Karimi M. News recommender systems-Survey and roads ahead.
Information Processing & Management,2018,54(6):1203-1227
|
CSCD被引
4
次
|
|
|
|
|
9.
Liu D R. Recommending blog articles based on popular event trend analysis.
Information Sciences,2015,305:302-319
|
CSCD被引
4
次
|
|
|
|
|
10.
Jonnalagedda N. Personalized news recommendation using twitter.
2013 IEEE/WIC/ACM International Joint Conferences on Web Intelligence (WI) and Intelligent Agent Technologies (IAT),2013:21-25
|
CSCD被引
1
次
|
|
|
|
|
11.
Natarajan S. Recommending news based on hybrid user profile, popularity, trends, and location.
2016 International Conference on Collaboration Technologies and Systems (CTS),2016:204-211
|
CSCD被引
1
次
|
|
|
|
|
12.
Zhang S. Deep learning based recommender system.
ACM Computing Surveys,2020,52(1):1-38
|
CSCD被引
73
次
|
|
|
|
|
13.
黄立威. 基于深度学习的推荐系统研究综述.
计算机学报,2018,41(7):1619-1647
|
CSCD被引
133
次
|
|
|
|
|
14.
Okura S. Embedding-based news recommendation for millions of users.
Proceedings of the 23rd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining,2017:1933-1942
|
CSCD被引
14
次
|
|
|
|
|
15.
Gao J. Fine-grained deep knowledge-aware network for news recommendation with selfattention.
2018 IEEE/WIC/ACM International Conference on Web Intelligence (WI),2018:81-88
|
CSCD被引
1
次
|
|
|
|
|
16.
Wu C H. Neural news recommendation with multi-head self-attention.
Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP),2019:6390-6395
|
CSCD被引
2
次
|
|
|
|
|
17.
Zhu Q N. DAN: Deep attention neural network for news recommendation.
Proceedings of the AAAI Conference on Artificial Intelligence,2019,33:5973-5980
|
CSCD被引
2
次
|
|
|
|
|
18.
Sarwar B. Itembased collaborative filtering recommendation algorithms.
WWW'01: Proceedings of the 10th International Conference on World Wide Web,2001:285-295
|
CSCD被引
1
次
|
|
|
|
|
19.
He X N. Neural collaborative filtering.
Proceedings of the 26th International Conference on World Wide Web,2017:173-182
|
CSCD被引
87
次
|
|
|
|
|
20.
Wang H W. DKN: Deep knowledge-aware network for news recommendation.
WWW'18: Proceedings of the 2018 World Wide Web Conference,2018:1835-1844
|
CSCD被引
1
次
|
|
|
|
|
了解气象卫星更多信息，请访问