基于迁移学习的主题感知增强的出版物推荐研究  

Publication Recommendation Based on Enhanced Topic Awareness with Transfer Learning

作　　者：沈阳泰 齐江蕾 丁浩 Shen Yangtai;Qi Jianglei;Ding Hao(School of Information Management,Nanjing University,Nanjing 210023,China;School of Civil Affairs and Social Work,Changsha Social Work College,Changsha 410004,China;School of Management,Nanjing University of Posts and Telecommunications,Nanjing 210003,China)

机构地区：[1]南京大学信息管理学院,南京210023 [2]长沙民政职业技术学院民政与社会工作学院,长沙410004 [3]南京邮电大学管理学院,南京210003

出　　处：《数据分析与知识发现》2025年第1期145-153,共9页Data Analysis and Knowledge Discovery

基　　金：国家社会科学基金重大项目(项目编号:20&ZD154);江苏省研究生科研与实践创新计划项目(项目编号:KYCX23_0079)的研究成果之一。

摘　　要：【目的】针对出版物推荐领域可能存在的数据稀疏性问题,提出一种基于LDA与迁移学习的潜在非负因子分解主题推荐模型,提高在数据稀疏场景中推荐的准确率。【方法】使用非负矩阵分解填充非负数据的高维稀疏矩阵,基于LDA与非负矩阵分解构建隐含主题模型,充分考虑用户评论信息的主题分布特征,进一步将用户不同维度的信息应用到评分预测中,缓解数据的稀疏性。同时引入迁移学习机制,从相关的其他类别出版物预训练模型中提取和迁移模型参数,协助完成目标模型特征学习任务,提高对冷门出版物推荐的有效性。【结果】在三个出版物数据集中与三种基线方法进行对比实验,本文模型的精确率、F1值和NDCG平均为0.7732、0.7085和0.7468,各指标结果总体优于其他基线模型。【局限】当系统中用户数量过少时,需通过其他方法进行冷启动。【结论】本文所提方法对用户兴趣特征泛化能力强,能进一步缓解模型中的流行度偏置以及数据稀疏性问题,有效提高出版物推荐的准确率。[Objective]This paper proposes a latent non-negative factorization topic recommendation model based on LDA and transfer learning to improve recommendation accuracy in sparse data scenarios.The new model aims to address the data sparsity issue in publication recommendations.[Methods]We used non-negative matrix factorization to fill the high-dimensional sparse matrix of non-negative data.Then,we constructed a latent topic model based on LDA and non-negative matrix factorization,fully considering the thematic distribution characteristics of user reviews.Additionally,we applied different dimensions of user information to rating prediction to mitigate data sparsity.Finally,we introduced a transfer learning mechanism to extract and transfer model parameters from pre-trained models of related publication categories.This mechanism assisted the feature learning for the target model data and improved the effectiveness of the recommendation for less popular publications.[Results]We conducted comparative experiments against three baseline methods with three publication datasets.The proposed model achieved average precision,F1 score,and NDCG of 0.7732,0.7085,and 0.7468.The model’s overall performance surpasses other baseline models.[Limitations]When the number of users in the system is too small,other methods are needed for cold-start situations.[Conclusions]The proposed method has strong generalization capabilities for user interest features,alleviates popularity bias and data sparsity,and effectively improves the accuracy of publication recommendations.

关 键 词：推荐系统 迁移学习 出版物推荐 流行度偏差 LDA 主题模型 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]