基于潜在主题分布和长、短期用户表示的新闻推荐模型  

News Recommendation with Latent Topic Distribution and Long and Short-Term User Representations

作　　者：唐娇 张力生[1] 桑春艳[1] Tang Jiao;Zhang Lisheng;Sang Chunyan(School of Software Engineering,Chongqing University of Posts and Telecommunications)

机构地区：[1]重庆邮电大学软件工程学院,重庆400065

出　　处：《数据分析与知识发现》2022年第9期52-64,共13页Data Analysis and Knowledge Discovery

基　　金：国家自然科学基金项目(项目编号:62002037);重庆市自然科学基金项目(项目编号:cstc2019jcyj-msxmX0588)的研究成果之一。

摘　　要：【目的】在充分利用新闻文本内容、附加信息的基础上,探究用户的当前关注和稳定偏好,弥补现有新闻推荐方法在利用新闻内容信息和探索用户长、短期混合兴趣等方面的不足。【方法】构建了一种融合不同类型新闻信息的新闻表示模型,对新闻的标题、摘要、正文等文本内容,以及显式主题、潜在主题等附加信息进行有效利用;在此基础上,构建一种可以刻画用户长、短期兴趣用户表示模型,探究用户的当前关注和稳定偏好。【结果】所提模型在两个大规模新闻推荐数据集上的性能分别达到了69.51%(AUC)、34.09%(MRR)、37.25%(nDCG@5)、43.01%(nDCG@10)以及66.05%(AUC)、30.93%(MRR)、34.30%(nDCG@5)、40.46%(nDCG@10),稳定超越7个基准模型。【局限】对历史行为稀疏的用户考虑不足,后续可针对用户冷启动场景作出适当推荐。【结论】所提模型利用先进的自然语言处理技术学习了信息量比较丰富的新闻和用户表示向量,其设计思路能有效提高新闻推荐的性能。[Objective] This paper proposes a news recommendation model based on contents and additional information on users’ current preferences, aiming to improve the performance of the existing ones. [Methods] We estblished a news representation model integrating the titles, abstracts, full-texts, as well as explicit and potential topics. We also built a user representation model utilizing the long and short-term user interests as well as their current concerns and preferences. [Results] We examined the proposed model with two large-scale news recommendation datasets. It reached 69.51% on AUC, 34.09% on MRR, 37.25% on nDCG@5, and 43.01% on nDCG@10 with the first dataset. For the second one, we had 66.05% on AUC, 30.93% on MRR, 34.30% on nDCG@5, and 40.46% on nDCG@10, which were all higher than the seven baseline models. [Limitations] More research is needed to study users with few historical behaviors. [Conclusions] The proposed model could create vectors for news contents and user representations using advanced natural language processing techniques. It also effectively improves the performance of news recommendation models.

关 键 词：新闻推荐 主题模型 神经网络 注意力机制 

分 类 号：TP393[自动化与计算机技术—计算机应用技术] G250[自动化与计算机技术—计算机科学与技术]