MIAR: Interest-Activated News Recommendation by Fusing Multichannel Information

Yang, Zhenyu; Cui, Laiping; Wang, Xuesong; Zhang, Tong; Cheng, Yuhu

doi:10.1109/tcss.2022.3201944

Cited by 3 publications

(2 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Recently, to take into account the impact of users' interest, deep learning-based models have been proposed to model the complex user-news interactions, and capture the dynamic properties of news and users. 3,8,[20][21][22][23][24][25][26][27][28] For example, Okura et al 3 proposed to learn the user representation from the news viewed by the user through gate recurrent unit (GRU) and study the news representation from the news content through the automatic encoder. Ji et al 20 designed the news feature extractor temporal-dimensional attention convolutional neural network to learn news representation and proposed an improved sequence information extraction model, Rein-LSTM, to extract the user-click sequence feature.…”

Section: Related Researchmentioning

confidence: 99%

“…Recently, to take into account the impact of users’ interest, deep learning-based models have been proposed to model the complex user-news interactions, and capture the dynamic properties of news and users 3 , 8 , 20 – 28 For example, Okura et al 3 . proposed to learn the user representation from the news viewed by the user through gate recurrent unit (GRU) and study the news representation from the news content through the automatic encoder.…”

Section: Related Researchmentioning

confidence: 99%

See 1 more Smart Citation

Graph neural network news recommendation based on weight learning and preference decomposition

Lu,

2023

J. Electron. Imag.

View full text Add to dashboard Cite

Personalized news suggestions are an important technology to enhance people's online news reading experiences. How to better understand users and news representation is a major issue in news recommendation. The majority of cutting-edge news recommendation techniques mostly neglect the link between title and content, explicitly and implicitly. They neglect to take into account the effects of many prospective news preferences on people's behavior when they click on various news items. We first build a user-news interaction graph and then present the weight learning and preference decomposition (WLPD) news recommendation model for graph neural networks, which is based on WLPD. This model not only takes into account the impact of the relationship between news titles and content, explicit and implicit, on the likelihood that users will click on the news, but also takes into account the various potential preferences between users and news interaction. Finally, using actual news databases, we run a number of experiments. We discover that our model significantly improved in terms of accuracy and performance compared with other cutting-edge news recommendation techniques.

show abstract

Section: Related Researchmentioning

confidence: 99%

Section: Related Researchmentioning

confidence: 99%

Graph neural network news recommendation based on weight learning and preference decomposition

Lu,

2023

J. Electron. Imag.

View full text Add to dashboard Cite

show abstract

GDN-CMCF: A Gated Disentangled Network With Cross-Modality Consensus Fusion for Multimodal Named Entity Recognition

Huang,

He,

Dai

et al. 2024

IEEE Trans. Comput. Soc. Syst.

View full text Add to dashboard Cite

News recommendation model based on encoder graph neural network and bat optimization in online social multimedia art education

Yu,

Zhao,

Yin

et al. 2024

COMSIS J

View full text Add to dashboard Cite

At present, the existing news recommendation system fails to fully consider the semantic information of news, meanwhile, the uneven popularity of news will also cause the phenomenon of long tail. Therefore, we propose a novel news recommendation model based on encoder graph neural network and Bat optimization in online social networks. Firstly, Bat optimization algorithm is used to improve the effect of news clustering. Secondly, the concept of metadata is introduced into the graph neural network, and the ontology of learning resources based on knowledge points is established to realize the correlation between news resources. Finally, the model combining Convolutional Neural Network (CNN) and attention network is used to learn the representation of news, and Gate Recurrent Unit (GRU) is used to learn the short-term preferences of users from their recent reading history. We carry out experiments on real news datasets, and compared with other advanced methods, the proposed model has better evaluation indexes.

show abstract

MIAR: Interest-Activated News Recommendation by Fusing Multichannel Information

Cited by 3 publications

References 39 publications

Graph neural network news recommendation based on weight learning and preference decomposition

Graph neural network news recommendation based on weight learning and preference decomposition

GDN-CMCF: A Gated Disentangled Network With Cross-Modality Consensus Fusion for Multimodal Named Entity Recognition

News recommendation model based on encoder graph neural network and bat optimization in online social multimedia art education

Contact Info

Product

Resources

About