基于用户多重兴趣漂移特征权重的网络出版物推荐研究  

Online Publication Recommendation Based on Weighted Features of User Multiple Interest Drift

作　　者：钱聪 齐江蕾 丁浩 Qian Cong;Qi Jianglei;Ding Hao(School of Information Management,Nanjing University,Nanjing 210023,China;Department of Chinese Language and Literature,Hetao University,Bayannur 015000,China)

机构地区：[1]南京大学信息管理学院,南京210023 [2]河套学院汉语言文学系,巴彦淖尔015000

出　　处：《数据分析与知识发现》2023年第8期119-127,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);黄河几字弯文化创新研究基地开放课题重点项目(项目编号:JZW2022001);2022年江苏省研究生科研创新计划项目(项目编号:KYCX22_0074)的研究成果之一。

摘　　要：【目的】基于用户多重自适应偏好特征时间权重改进强化潜在因子模型,以提高推荐的准确性。【方法】基于时序潜在因子模型进一步融合兴趣遗忘特征、出版物兴趣重合度以及评论文本语义层面的相似度等用户不同时间段的偏好,通过偏好权重对用户评分矩阵加权并分解,以捕捉用户在每个时间对不同出版物的多重偏好变化。【结果】在三个数据集中与4种基于时序矩阵分解基线方法进行对比实验,结果表明本文模型的准确率相较于TDMF平均提高9.26个百分点,相比TMRevCo提高17.35个百分点,相比BPTF提高38.63个百分点,相比TCMF提高26.24个百分点,说明本文模型对于用户时序特征抽取更为准确。【局限】由于兴趣漂移演变分析依赖用户历史数据,当历史数据量过于稀疏时需采用用户其他信息进行冷启动。【结论】本文模型考虑用户的遗忘特征和评论演化特征,对于用户时序兴趣漂移的捕捉更有效,更能反映用户对出版物兴趣的演化关系,提高了推荐的准确率。[Objective]This paper improves the Reinforced Latent Factor Model with user multi-adaptive preference feature temporal weighting,aiming to improve the accuracy of recommendations.[Methods]Building upon the Temporal Potential Factor Model,we further integrated user preferences from different periods,such as interest forgetting features,publication interest overlap,and semantic similarity of comments.The user rating matrix is weighted and decomposed based on preference weights to capture the multiple preference changes of users towards different publications at different times.[Results]We conducted comparison experiments with four baseline methods based on temporal matrix factorization with three datasets.The proposed model’s precision was 9.26%higher than TDMF,17.35%higher than TMRevCo,38.63%higher than BPTF,and 26.24%higher than TCMF.This demonstrates that the proposed model is more accurate in extracting user temporal features.[Limitations]The analysis of interest drift evolution depends on historical user data.When the data is too sparse,alternative user information is required for a cold start.[Conclusions]The proposed model considers user forgetting and comment evolution features,effectively capturing user temporal interest drift and reflecting the evolving relationship of users’interest in publications.It improves the accuracy of recommendations.

关 键 词：时间序列 兴趣漂移 潜在因子 话题演化 推荐系统 

分 类 号：TP391[自动化与计算机技术—计算机应用技术] G350[自动化与计算机技术—计算机科学与技术]