[1]任秋臻,陈红梅,周丽华.基于时间信息表示学习的个性化推荐方法[J].计算机技术与发展,2023,33(01):34-41.[doi:10. 3969 / j. issn. 1673-629X. 2023. 01. 006]
　EN Qiu-zhen,CHEN Hong-mei,ZHOU Li-hua.Personalized Recommendation Method Based on TimeRepresentation Learning[J].,2023,33(01):34-41.[doi:10. 3969 / j. issn. 1673-629X. 2023. 01. 006]
点击复制

基于时间信息表示学习的个性化推荐方法()
分享到：

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
33
期数:
2023年01期
页码:
34-41
栏目:
大数据与云计算
出版日期:
2023-01-10

文章信息/Info

Title:
Personalized Recommendation Method Based on TimeRepresentation Learning
文章编号:
1673-629X(2023)01-0034-08
作者:
任秋臻; 陈红梅; 周丽华
云南大学 信息学院,云南 昆明 650500
Author(s):
EN Qiu-zhen; CHEN Hong-mei; ZHOU Li-hua
School of Information Science and Engineering,Yunnan University,Kunming 650500,China
关键词:
时间信息; 网络表示学习; 异质网络; 协同过滤; 个性化推荐
Keywords:
time information; network representation learning; heterogeneous networks; collaborative filtering; personalized recommendation
分类号:
TP391
DOI:
10. 3969 / j. issn. 1673-629X. 2023. 01. 006
摘要:
个性化推荐已成为现代智能化服务中的重要技术,时间信息是影响个性化推荐效果的重要因素。 然而现有基于网络表示学习的个性化推荐方法,有的将事物及其关系抽象为同质网络,忽视了固有　的异质性;有的虽将事物及其关系建模为异质网络,但没有较好地利用时间信息。 因此, 文中提出一种基于时间信息表示学习的个性化推荐方法( TimeRepresentation Learning Incorporating into User Collaborative Filtering,TRLIUCF) ,TRLIUCF 方法综合利用了评论的时间信息、文本信息、评分信息,获得了较好的推荐结果。 首先,根据评论文本提取评论情绪特征,并根据时间信息提取　评论时间特征,基于二者提出评论综合情绪-贡献值及其计算方法。 然后,基于评论综合情绪-贡献值和用户评论数据构建用户-商品-评论异质网络,并采用网络表示学习方法学习节点嵌入向量。 　最后,通过用户节点嵌入向量计算用户相似性,并采用基于用户的协同过滤进行 TOP-N 推荐。 在两个不同规模的真实数据集上的实验表明,与基准方法相比,TRLIUCF 方法提高了推荐精确率和召回率。
Abstract:
Personal recommendations have become an important technology in modern intelligent services, and time information is animportant factor affecting the effectiveness of personalized recommendations. However, some existing personalized recommendationmethods based on network representation learning abstract things and their relationships as homogeneous networks,ignoring the inherentheterogeneity;some model things and their relationships as heterogeneous networks, but do not make use of time information.Accordingly,we propose a personalized recommendation method based on Time Representation Learning Incorporating into UserCollaborative Filtering ( TRLIUCF) , which integrates temporal information, textual information, and rating information of reviews toobtain better results. Firstly,we extract the comment sentiment features based on the comment text,and extract the comment time features　based on the time information,and propose the comment integrated sentiment-contribution value and its calculation method. Then,a user-item-review heterogeneous network is created based on the comment integrated sentiment-contribution value and user review data,and anetwork representation learning method is used to learn the node embedding vector. Finally,user similarity is calculated by the embeddingvector of the user node and TOP - N recommendation is executed using user - based collaborative filtering. Experiments on two realdatasets of different sizes show that the TRLIUCF method improves recommendation precision and recall compared to the benchmarkmethod.

相似文献/References:

[1]臧玑珣,徐鑫航.基于网络嵌入的农产品销售推荐系统[J].计算机技术与发展,2022,32(10):209.[doi:10. 3969 / j. issn. 1673-629X. 2022. 10. 034]
　ZANG Ji-xun,XU Xin-hang.Recommendation System for Agricultural Products MarketingChannels Based on Network Embedding[J].,2022,32(01):209.[doi:10. 3969 / j. issn. 1673-629X. 2022. 10. 034]
[2]徐红艳,党依铭,冯 勇,等.融合时间信息的序列商品推荐模型[J].计算机技术与发展,2023,33(03):139.[doi:10. 3969 / j. issn. 1673-629X. 2023. 03. 021]
　XU Hong-yan,DANG Yi-ming,FENG Yong,et al.A Sequential Product Recommendation Model Integrating Time Information[J].,2023,33(01):139.[doi:10. 3969 / j. issn. 1673-629X. 2023. 03. 021]

更新日期/Last Update: 2023-01-10