一种使用全部评分提高推荐精度的方法 -- 西北工业大学学报,2017,35(5):928-934
论文:2017,Vol:35,Issue(5):928-934
引用本文:
程伟杰, 印桂生, 董宇欣, 董红斌, 张万松. 一种使用全部评分提高推荐精度的方法[J]. 西北工业大学学报
Cheng Weijie, Yin Guisheng, Dong Yuxin, Dong Hongbin, Zhang Wansong. A Method for Improving Recommendation Accuracy via All Rating History[J]. Northwestern polytechnical university

一种使用全部评分提高推荐精度的方法
程伟杰, 印桂生, 董宇欣, 董红斌, 张万松
哈尔滨工程大学 计算机科学与技术学院, 黑龙江 哈尔滨 150001
摘要:
传统的基于用户的协同过滤推荐算法只能使用用户在共同评价过的项目上的评分记录进行推荐,由于推荐系统中数据稀疏和冷启动问题的存在,用户共同评价的项目较少,导致了用户的大量评分记录中只有少部分的数据得到了利用,限制了推荐系统预测用户偏好的精度。为了利用用户的全部评分提高推荐系统的精度,定义了用于描述和区分不同项目的内部子信息,提出了将用户对项目的评分分解为对内部子信息评分的方法,该方法能够使用用户的全部评分记录分析用户的相似度,同时设计了考虑用户间共同评价项目比例的动态调节权重用于将基于全部评分的用户相似度与传统的基于共同评分的用户相似度进行混合,并将混合相似度用于预测用户对项目评分。实验结果表明:使用用户的全部评分记录能够提高推荐系统预测精度,动态调节权重比静态的混合权重更能改善推荐效果。
关键词:    协同过滤    推荐系统    数据稀疏    相似度    标签    平均绝对误差    均方根误差   
A Method for Improving Recommendation Accuracy via All Rating History
Cheng Weijie, Yin Guisheng, Dong Yuxin, Dong Hongbin, Zhang Wansong
College of Computer Science and Technology, Harbin Engineering University, Harbin 150001, China
Abstract:
In traditional user-based collaborative filtering algorithms, only users' ratings to shared items are utilized in recommendation. Due to the existence of data sparsity and cold-start problems, the amount of users' common rated items is not sufficient. As a result, only a small quantity of data in users' massive rating records can be considered, which limits the accuracy of recommender systems in predicting user's preferences. In order to use all the rating records to improve recommendation, this paper introduces items' internal description information (IDI) for describing and discriminating different items. Based on IDI, a method is proposed to derive users' ratings to items' internal description information from the ratings to items, so that users' similarity on users' all existed ratings can be calculated. For mixing users' similarity based on all the ratings with traditional similarity based on those ratings to users' shared items, we design a dynamic adjusting weight considering the proportion of users' common items in their all rated items. Then the mixed similarity is used to predict users' ratings to unobserved items. The experiment results show that, all the ratings can be used to improve the accuracy of recommender systems, and the proposed dynamic adjusting weight overpowers the static hybrid weight.
Key words:    collaborative filtering    recommender system    dada sparsity    similarity    tag    mean absolute error    root mean square error   
收稿日期: 2016-12-28     修回日期:
DOI:
基金项目: 国家自然科学基金(61472095、61272186)资助
通讯作者:     Email:
作者简介: 程伟杰(1986-),哈尔滨工程大学博士研究生,主要从事数据挖掘、机器学习和推荐系统研究。
相关功能
PDF(1053KB) Free
打印本文
把本文推荐给朋友
作者相关文章
程伟杰  在本刊中的所有文章
印桂生  在本刊中的所有文章
董宇欣  在本刊中的所有文章
董红斌  在本刊中的所有文章
张万松  在本刊中的所有文章

参考文献:
[1] 于洪,李俊华.一种解决新项目冷启动问题的推荐算法[J]. 软件学报, 2015, 26(6):1395-1408 Yu Hong, Li Junhua. Algorithm to Solve the Cold-Start Problem in New Item Recommendations[J]. Journal of Software, 2015, 26(6):1395-1408(in Chinese)
[2] Patra B K, Launonen R, Ollikainen V, et al. A New Similarity Measure Using Bhattacharyya Coefficient for Collaborative Filtering in Sparse Data[J]. Knowledge-Based Systems, 2015, 82(2):163-177
[3] Sen S, Vig J, Riedl J. Tagommenders:Connecting Users to Items through Tags[C]//18th International World Wide Web Conference, 2009:671-680
[4] Gedikli F, Jannach D. Improving Recommendation Accuracy Based on Item-Specific Tag Preferences[J]. ACM Trans on Intelligent Systems & Technology, 2013, 4(1):43-55
[5] Qi Q, Chen Z, Liu J, et al. Using Inferred Tag Ratings to Improve User-Based Collaborative Filtering[C]//Proceedings of the 27th Annual ACM Symposium on Applied Computing, 2012:2008-2013
[6] He X S, Zhou M Y, Zhuo Z, et al. Predicting Online Ratings Based on the Opinion Spreading Process[J]. Physica A Statistical Mechanics & Its Applications, 2015, 436:658-664
[7] Gan M. COUSIN:A Network-Based Regression Model for Personalized Recommendations[J]. Decision Support Systems, 2015, 82:58-68
[8] Gao H, Tang J, Hu X, et al. Content-Aware Point of Interest Recommendation on Location-Based Social Networks[C]//Twenty-Ninth AAAI Conference on Artificial Intelligence, 2015:1721-1727
[9] Liu H, Hu Z, Mian A, et al. A New User Similarity Model to Improve the Accuracy of Collaborative Filtering[J]. Knowledge-Based Systems, 2014, 56(3):156-166
[10] Jabeen F, Khusro S, Majid A, et al. Semantics Discovery in Social Tagging Systems:A Review[J]. Multimedia Tools & Applications, 2014, 75(1):1-33
[11] Chen L, Chen G, Wang F. Recommender Systems Based on User Reviews:the State of the Art[J]. User Modeling and User-Adapted Interaction, 2015, 25(2):99-154
[12] Ning X, Karypis G. SLIM:Sparse Linear Methods for Top-N Recommender Systems[C]//201111th IEEE International Conference on Data Mining, 2011:497-506
[13] Albadvi A, Shahbazi M. A Hybrid Recommendation Technique Based on Product Category Attributes[J]. Expert Systems with Applications, 2009, 36(9):11480-11488
[14] Liang H, Xu Y, Li Y, et al. Connecting Users and Items with Weighted Tags for Personalized Item Recommendations[C]//Proceedings of the ACM Conference on Hypertext and Hypermedia, 2010:51-60
[15] Goldberg K, Roeder T, Gupta D, et al. Eigentaste:A Constant Time Collaborative Filtering Algorithm[J]. Information Retrieval, 2001, 4(2):133-151
[16] Harper F M, Konstan J A. The MovieLens Datasets:History and Context[J]. ACM Trans on Interactive Intelligent Systems, 2016, 5(4):1-19
[17] Feng H, Tian J, Wang H J, et al. Personalized Recommendations Based on Time-Weighted Overlapping Community Detection[J]. Information & Management, 2015, 52(7):789-800
[18] 孟祥武, 刘树栋, 张玉洁,等. 社会化推荐系统研究[J]. 软件学报, 2015, 26(6):1356-1372 Meng Xiangwu, Liu Shudong, Zhang Yujie, et al. Research on Social Recommender Systems[J]. Journal of Software, 2015,26(6):1356-1372(in Chinese)
[19] Sun Z, Guo G, Zhang J. Exploiting implicit item relationships for recommender systems[C]//International Conference on User Modeling, Adaptation, and Personalization, 2015:397-402