本文已被:浏览 2274次 下载 2149次
Received:December 30, 2017 Revised:January 16, 2018
Received:December 30, 2017 Revised:January 16, 2018
中文摘要: 在面向用户的文章收集系统中,用户会将自己喜欢的文章收集起来构成自己的偏好文章集合,理解用户为何喜欢特定文章、如何精确的找到用户喜欢的文章目前成为了一个重要的研究课题.本文通过基于面向用户的文章收集系统中的一些相关信息,比如文本信息、标签等,来辅助推荐系统更好的进行文章的推荐.文中提出了基于标签卷积神经网络的文本推荐算法,结合神经网络和协同过滤算法的同时,将标签加入到神经网络的设计中.通过在真实的citeulike数据集进行的实验和验证,使用本文的模型可以有效的提高对用户偏好文章预测的准确性.
Abstract:In user-oriented article collection system, users construct their collection sets by adding articles which they are interested in, studying why users desire specific articles and find the specific articles is particularly an interesting issue in social science. In this paper, we present the prediction users' preference on articles by considering content information, i.e. semantic information and tags. In this study, we propose a new model which jointly performs deep representation learning for the content information and collaborative filtering for the collection matrix. Extensive experiments on the real-world datasets show that it can significantly advance the state-of-the-art.
文章编号: 中图分类号: 文献标志码:
基金项目:
Author Name | Affiliation | |
MA Xiao-Yang | School of Computer Science, Fudan University, Shanghai 201203, China | 15210240042@fudan.edu.cn |
ZHANG Mi | School of Computer Science, Fudan University, Shanghai 201203, China |
Author Name | Affiliation | |
MA Xiao-Yang | School of Computer Science, Fudan University, Shanghai 201203, China | 15210240042@fudan.edu.cn |
ZHANG Mi | School of Computer Science, Fudan University, Shanghai 201203, China |
引用文本:
马骁烊,张谧.基于标签卷积神经网络的文本推荐算法.计算机系统应用,2018,27(8):132-137
MA Xiao-Yang,ZHANG Mi.Personalized Academic Article Recommendation with Tagged Convolutional Nets.COMPUTER SYSTEMS APPLICATIONS,2018,27(8):132-137
马骁烊,张谧.基于标签卷积神经网络的文本推荐算法.计算机系统应用,2018,27(8):132-137
MA Xiao-Yang,ZHANG Mi.Personalized Academic Article Recommendation with Tagged Convolutional Nets.COMPUTER SYSTEMS APPLICATIONS,2018,27(8):132-137