帮助 关于我们

返回检索结果

基于终身机器学习的主题挖掘与评分预测联合模型
Topic Mining and Ratings Prediction Joint Model Based on Lifelong Machine Learning

查看参考文献16篇

文摘 为充分利用历史知识,提高评分预测精度,基于终身机器学习(LML)机制提出一种同时挖掘用户评分和评论的推荐模型。在执行任务时积累知识并用于后续任务的训练,提高评分预测精度。在真实数据集上的实验结果表明,与无LML 能力的模型相比,该模型预测评分的均方误差降低5.4‰,且随着知识的积累,误差不断降低,提高了主题词语分类的精度。
其他语种文摘 In order to make full use of the historical knowledge and improve the accuracy of rating prediction,a recommendation model based on Lifelong Machine Learning (LML) is proposed to mine both user ratings and comments.The model accumulates knowledge from previous tasks and utilizes it in future tasks to help improve the rating prediction accuracy.Experimental results on real datasets show that compared with models without LML ability,the mean square error of the predicted ratings of this model is reduced by 5.4‰,and with the accumulation of knowledge,its error is continuely dropped.The accuracy of topic word classification results is improved.
来源 计算机工程 ,2019,45(6):237-241,248 【扩展库】
DOI 10.19678/j.issn.1000-3428.0051131
关键词 文本主题模型 ; 推荐算法 ; 终身机器学习 ; 评分预测 ; 协同过滤
地址

大连理工大学电子信息与电气工程学部, 辽宁, 大连, 116024

语种 中文
文献类型 研究性论文
ISSN 1000-3428
学科 自动化技术、计算机技术
基金 国家自然科学基金重点项目 ;  中央高校基本科研业务费专项资金
文献收藏号 CSCD:6513231

参考文献 共 16 共1页

1.  金紫嫣. 一种带标签的协同过滤广告推荐算法. 计算机工程,2018,44(4):236-242,247 被引 3    
2.  Mcauley J. From amateurs to connoisseurs: modeling the evolution of user expertise through online reviews. Proceedings of the 22nd International Conference on World Wide Web,2015:897-908 被引 1    
3.  Mnih A. Probabilistic matrix factorization. Proceedings of the 20th International Conference on Neural Information Processing Systems,2008:1257-1264 被引 2    
4.  Wang Chong. Collaborative topic modeling for recommending scientific articles. Proceedings of the 17th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining,2011:448-456 被引 45    
5.  Mcauley J. Hidden factors and hidden topics: understanding rating dimensions with review text. Proceedings of the 7th ACM Conference on Recommender Systems,2013:165-172 被引 31    
6.  Diao Qiming. Jointly modeling aspects,ratings and sentiments for movie recommendation. Proceedings of the 20th ACM SIGKDD International Conference on Knowledge Discovery and Data Mining,2014:193-202 被引 5    
7.  Ling Guang. Ratings meet reviews,a combined approach to recommend. Proceedings of the 8th ACM Conference on Recom-mender Systems,2014:105-112 被引 1    
8.  Chen Zhiyuan. Lifelong machine learning,2016 被引 1    
9.  Hu Guangneng. A synthetic approach for recommendation: combining ratings,social relations,and reviews. Proceedings of the 24th International Conference on Artificial Intelligence,2015:1756-1762 被引 1    
10.  Thrun S. Is learning the n-th thing any easier than learning the first. Proceedings of the 8th International Conference on Neural Information Processing Systems,1996:640-646 被引 2    
11.  Fei Geli. Learning cumulatively to become more knowledgeable. Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining,2016:1565-1574 被引 2    
12.  Shu Lei. Lifelong-rl: lifelong relaxation labeling for separating entities and aspects in opinion targets,2018 被引 1    
13.  Chen Zhiyuan. Topic modeling using topics from many domains,lifelong learning and big data. Proceedings of International Conference on Machine Learning,2014:703-711 被引 1    
14.  Kapoor A. Principles of lifelong learning for predictive user modeling. Proceedings of International Conference on User Modeling,2007:37-46 被引 1    
15.  Liu Qian. Improving opinion aspect extraction using semantic similarity and aspect associations,2018 被引 1    
16.  Blei D M. Latent dirichlet allocation. Journal of Machine Learning Research,2003,3:993-1022 被引 1298    
引证文献 2

1 王璐 连续时间区间内的频繁词序列挖掘算法 计算机工程,2022,48(2):79-85,91
被引 0 次

2 雷恒林 基于Hellinger距离与词向量的终身机器学习主题模型 计算机工程,2022,48(11):89-95
被引 0 次

显示所有2篇文献

论文科学数据集
PlumX Metrics
相关文献

 作者相关
 关键词相关
 参考文献相关

版权所有 ©2008 中国科学院文献情报中心 制作维护:中国科学院文献情报中心
地址:北京中关村北四环西路33号 邮政编码:100190 联系电话:(010)82627496 E-mail:cscd@mail.las.ac.cn 京ICP备05002861号-4 | 京公网安备11010802043238号