基于多属性评分隐表征学习的群组推荐算法  

Group Recommendation Algorithms Based on Implicit Representation Learning of Multi-attribute Ratings

作　　者：张纯金[1] 郭盛辉 纪淑娟[2] 杨伟[2] 伊磊 Zhang Chunjin;Guo Shenghui;Ji Shujuan;Yang Wei;Yi Lei(Network Security and Information Office,Shandong University of Science and Technology,Qingdao 266590,China;Shandong Provincial Key Laboratory of Wisdom Mine Information Technology,Shandong University of Science and Technology,Qingdao 266590,China)

机构地区：[1]山东科技大学网络安全与信息化办公室,青岛266590 [2]山东省智慧矿山信息技术重点实验室(山东科技大学),青岛266590

出　　处：《数据分析与知识发现》2020年第12期120-135,共16页Data Analysis and Knowledge Discovery

基　　金：青岛社会科学规划研究项目“大数据背景下跨境电商中产品信息挖掘与推荐研究”(项目编号:QDSKL1801138);国家自然科学基金项目“面向大数据流的信用攻击群体及关键人物发现方法研究”(项目编号:71772107)和国家自然科学基金项目“复杂属性网络的多视角表示学习关键技术研究”(项目编号:62072288)的研究成果之一。

摘　　要：【目的】克服个体用户表征学习受个体用户评分稀疏性影响严重的问题,提高推荐算法的准确率和反应速度。【方法】提出一种基于神经网络的多属性评分隐表征学习方法,并应用该方法从用户群组和项目两个维度学习多属性评分的隐表征,最后分别通过用户群组偏好匹配和项目吸引力计算实现两个群组推荐。【结果】基于TripAdvisor数据集的实验结果表明:本文算法的准确率、时间性能优于典型的多属性推荐算法和群组推荐算法;准确率略差于个体推荐算法,但在线和离线运行时间较个性化推荐算法分别至少降低30%和50%;用户群组的隐表征学习相比项目的隐表征学习对推荐性能的提高作用更明显。【局限】由于真实群组数据难以获取,仅基于某种聚类算法生成虚拟群组,因此群组较理想化。虚拟群组的偏好比真实群组的偏好可能更易聚合。【结论】基于神经网络学习群组用户的隐表征(即聚合群组用户的偏好)和项目的隐表征,可以有效提高群组推荐算法和多属性推荐算法的准确率和召回率,效果非常接近最新的个性化推荐算法。[Objective] This paper addresses the issues facing user representation learning due to the sparsity of their ratings, aiming to improve the performance of recommendation algorithm. [Methods] We proposed a neural network-based method to learn the implicit representation of multi-attribute ratings from user groups and individual items. Then, we conducted two group-oriented recommendations by matching their learned representations with preferences as well as calculating the attraction of each item. [Results] We examined our method with TripAdvisor data set and found the accuracy and time performance of the proposed algorithms were better than the typical multi-attribute ones and group ones. Compared to the personalized recommendation algorithm, the accuracies of our algorithms were slightly worse, but their online and offline running time was reduced by more than 30% and 50%, repectively. The recommendation results from user group based algorithm outperformed the item based one. [Limitations] We generated virtual groups based on clustering algorithm and their preferences were aggregated more effecitvely than the real world ones. [Conclusions] The proposed algorithms effectively improve the recommendation results.

关 键 词：群组推荐算法 多属性评分 隐表征学习 评分矩阵 神经网络 

分 类 号：TP393[自动化与计算机技术—计算机应用技术]