检索结果-内蒙古大学图书馆

recommendation algorithm of influence and trust relationship

MULTIMEDIA TOOLS AND APPLICATIONS 2022年第11期81卷 15635-15652页

作者： Zhang Li Chen XiaoBo Jiangsu Univ Technol Sch Comp Engn Changzhou 213001 Jiangsu Peoples R China Peoples Bank China Changzhou City Ctr Branch Changzhou 213001 Jiangsu Peoples R China

The recommendation system recommends information and services to users by collecting and analyzing user behaviors. Many current studies have shown that recommendation algorithms that integrate social network information can effectively improve recommendation performance. Most of the existing social recommendation algorithms assume that the trust relationship between users is singular and homogeneous. These social recommendation algorithms generally ignore two problems: (i) in a network of trust relationships, each user has various friends and trust relationships, which have an impact on user ratings. (ii) each user with different social status, which influences also affects the ratings between users. Propose a social network recommendation algorithm (social Strength Trust recommendation algorithm, SSTRA) in this paper. Firstly, the algorithm uses the different out-degree and in-degree relationships among different users to calculate the different trust strengths of each user in social networks;secondly, it calculates the social influence of different users through the social ranking algorithm (SocailRank);thirdly, it will be based on the trust strength relationship of social networks and the social influence of users are integrated into the probability matrix factorization model. This method can achieve the purpose of optimizing recommendation results. The experimental results compared on the CiaoDVD dataset show that: Compared with the socialMF, SoRec, RSTE, PMF, and Trust algorithms, the average MAE has increased by 1.33%, 1.69%, 4.88%, 11.17% and 220.41%, and the average RMSE has increased by 1.47%, 1.9%, 5.06%, 7.27%, 217.55%. The experimental results compared on the Ciao dataset show that: Compared with the socialMF, SoRec, RSTE, PMF, and Trust algorithms, the average MAE is increased by 4.83%, 5.05%, 1.96%, 5.58%, 143.39%, and the average RMSE is increased by 1.76%, 2.17%, 2.1%, 2.38%, 151.1%. Experimental results show that the algorithm has obvious advantages

关键词： social network social influence Trust relationship social recommendation algorithm Probability matrix factorization

来源：评论

学校读者我要写书评

暂无评论

Using Graph Neural Networks for social recommendations

引用

algorithmS 2023年第11期16卷

作者： Tallapally, Dharahas Wang, John Potika, Katerina Eirinaki, Magdalini San Jose State Univ Dept Comp Sci San Jose CA 95192 USA San Jose State Univ Dept Comp Engn San Jose CA 95192 USA

Recommender systems have revolutionized the way users discover and engage with content. Moving beyond the collaborative filtering approach, most modern recommender systems leverage additional sources of information, such as context and social network data. Such data can be modeled using graphs, and the recent advances in Graph Neural Networks have led to the prominence of a new family of graph-based recommender system algorithms. In this work, we propose the RelationalNet algorithm, which not only models user-item, and user-user relationships but also item-item relationships with graphs and uses them as input to the recommendation process. The rationale for utilizing item-item interactions is to enrich the item embeddings by leveraging the similarities between items. By using Graph Neural Networks (GNNs), RelationalNet incorporates social influence and similar item influence into the recommendation process and captures more accurate user interests, especially when traditional methods fall short due to data sparsity. Such models improve the accuracy and effectiveness of recommendation systems by leveraging social connections and item interactions. Results demonstrate that RelationalNet outperforms current state-of-the-art social recommendation algorithms.

关键词： social recommendation algorithm graph neural networks recommender systems social network influence diffusion

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：