融合标签和内容信息的矩阵分解推荐方法  

A Matrix Factorization Recommendation Method with Tags and Contents

作　　者：马莹雪 甘明鑫[1] 肖克峻 Ma Yingxue;Gan Mingxin;Xiao Kejun(School of Economics and Management,University of Science and Technology Beijing,Beijing 100083,China)

机构地区：[1]北京科技大学经济管理学院,北京100083

出　　处：《数据分析与知识发现》2021年第5期71-82,共12页Data Analysis and Knowledge Discovery

基　　金：国家自然科学基金项目(项目编号:71871019,71471016)的研究成果之一。

摘　　要：【目的】针对推荐系统的异构信息融合问题,提出融合标签和内容数据的矩阵分解方法 TCMF,减小预测误差,克服评分数据稀疏问题,提升矩阵分解算法鲁棒性。【方法】使用Embedding实现内容文本数据的结构化,使用卷积神经网络(CNN)提取深层次内容特征,利用深度神经网络(DNN)融合内容与标签信息得到综合特征,基于矩阵分解算法提出TCMF评分预测方法。在真实电影数据集上的实验进一步探究了不同特征融合方式、不同电影内容和正则化参数对算法预测性能的影响。【结果】在MovieLens-20m数据集上的实验显示,TCMF降低了电影评分预测误差,实现的最低RMSE为0.829 5,最低MAE为0.618 9,相比于对比方法在RMSE和MAE上的最高降幅达到9.62%和14.17%。【局限】由于缺少用户信息,TCMF在表征用户的个性化特征上有所欠缺。【结论】融合异构的标签和内容信息不仅能够降低用户评分预测误差,而且可以提高预测算法的鲁棒性。[Objective] This paper proposes a matrix factorization method(TCMF) integrating tags and contents,aiming to address the issue of heterogeneous information fusion in recommendation system. It tries to reduce prediction errors, overcome the problem of data sparsity, and improve the robustness of matrix factorization algorithm. [Methods] We transformed textual message to structured data with the help of embedding. Then, we extracted hidden features with CNN. Third, we merged the features of movie contents and tags with DNN to obtain comprehensive features. Finally, we proposed the TCMF based on matrix factorization algorithm and evaluated its performance with movie rating dataset(MovieLens-20 m). [Results] The TCMF reduced the error of movie rating predictions(with the lowest RMSE of 0.829 5 and the lowest MAE of 0.618 9). Compared with the exisiting methods, the maxium reduction of RMSE and MAE were 9.62% and 14.17%. [Limitations] Due to the lack of information, the TCMF cannot characterize users’ personalized features. [Conclusions] The proposed model not only reduces the error of rating prediction, but also improves robustness of algorithm.

关 键 词：推荐算法 矩阵分解 深度学习 异构信息 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]