基于评论方面级用户偏好迁移的跨领域推荐算法  

Cross-domain Recommendation Based on Review Aspect-level User Preference Transfer

作　　者：张佳 董守斌[1,2] ZHANG Jia;DONG Shou-bin(School of Computer Science and Engineering,South China University of Technology,Guangzhou 510006,China;Zhongshan Institute of Modern Industrial Technology of SCUT,Zhongshan,Guangdong 528437,China)

机构地区：[1]华南理工大学计算机科学与工程学院,广州510006 [2]中山市华南理工大学现代产业技术研究院,广东中山528437

出　　处：《计算机科学》2022年第9期41-47,共7页Computer Science

摘　　要：为解决推荐系统中数据稀疏造成的用户冷启动问题,文中提出了一种基于方面级用户偏好迁移的跨领域推荐算法(Cross-Domain Recommendation via Review Aspect-Level User Preference Transfer, CAUT),设计了基于两阶段生成对抗网络的用户方面级偏好跨领域迁移结构,通过用户历史评论挖掘用户细粒度方面级偏好。CAUT利用预训练源领域编码器参数对目标领域编码器进行参数初始化,在固定源领域编码器参数的同时引入领域鉴别器,以解决源领域与目标领域数据分布差异的问题,进而可以有效利用源领域的丰富数据,缓解目标领域数据稀疏造成的用户冷启动问题。在亚马逊电商平台真实数据集上进行了实验,结果表明,与最新算法相比,CAUT在用户对商品的评分预测均方根误差(RMSE)指标上有明显的提升,说明CAUT可有效缓解用户冷启动问题。In order to solve the user cold-start problem caused by data-sparse in recommender system, this paper proposes a cross-domain recommendation algorithm based on aspect-level user preference transfer, named CAUT.CAUT is devised to learn aspect transfer across domains from a two-stage generative adversarial network and extract aspect-level user fine-grained prefe-rence from reviews.The data distribution misalignment between source and target domains is eliminated by fixing source domain encoder parameters and designing a domain discriminator.Then the user cold-start problem caused by data-sparse in the target domain could be alleviated by utilizing source domain data via CAUT.Experiments on real-world datasets show that the proposed CAUT outperforms SOTA models significantly in rating prediction RMSE indicator, suggesting that CAUT can effectively solve the user cold-start problem.

关 键 词：跨领域推荐 方面级用户偏好 用户冷启动 生成对抗网络 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]