期刊文献+

融合用户兴趣漂移特征的个性化推荐研究 被引量:11

Research on Personalized Recommendation Combining User Interest Drift
原文传递
导出
摘要 [目的/意义]基于社交网络用户短期兴趣和长期兴趣,挖掘用户不同时间窗口下长短期兴趣,能够提高用户兴趣发现的准确性,解决推荐系统不能适应用户兴趣变化的问题。[方法/过程]通过对社交网络用户兴趣的研究发现,社交网络用户兴趣可以分为短期兴趣和长期兴趣,据此构建融合用户兴趣漂移特征的个性化推荐模型。采用时间窗口的方法挖掘用户短期兴趣,利用遗忘曲线跟踪用户长期兴趣变化。在此基础上对用户进行聚类,根据用户聚类结果为用户推荐兴趣相似用户。并以微博真实数据为例进行实证。[结果/结论]融合用户兴趣漂移特征的个性化推荐模型能够较准确地发现用户兴趣漂移特征,满足用户个性化信息需求。[局限]仅使用"微博"这一应用广泛的网络社交平台进行实证,未能从多个网络社交平台进一步验证模型的可行性和准确性。 [Purpose/significance] Based on the short-term and long-term interests of social network users, mining the long-term and short-term interests of users under different time Windows can improve the accuracy of user interest discovery and solve the problem that the recommendation system cannot adapt to the change of users’ interests.[Method/process] Through the study of social network users’ interests, it is found that social network users’ interests can be divided into short-term interests and long-term interests, and based on this, a personalized recommendation model integrating user interest drift characteristics is built.The method of time window is used to mine users’ short-term interest and the forgetting curve is used to track users’ long-term interest.On this basis, user clustering is carried out, and users with similar interests are recommended according to the clustering results.And take the real data of Weibo as an example to carry on the demonstration.[Result/conclusion] Personalized recommendation model integrating user interest drift features can find user interest drift features more accurately and meet user’s personalized information needs.[Limitations] This paper only uses “Weibo”,a widely used social network platform, to conduct empirical study, failing to further verify the feasibility and accuracy of the model from multiple social network platforms.
作者 蒋武轩 易明 汪玲 Jiang Wuxuan
出处 《情报理论与实践》 CSSCI 北大核心 2022年第1期38-45,37,共9页 Information Studies:Theory & Application
基金 国家社会科学基金重点项目“在线健康社区知识共创机理及引导机制研究”研究成果,项目编号:21ATQ006。
关键词 兴趣漂移 行为特征 人类行为动力学 个性化推荐 interest drift behavioral characteristics dynamics of human behavior personalized recommendation
  • 相关文献

参考文献7

二级参考文献211

  • 1江志恒,刘乃芩.论遗忘函数——关于记忆心理学的数学讨论[J].心理科学进展,1988(3):56-60. 被引量:13
  • 2邢春晓,高凤荣,战思南,周立柱.适应用户兴趣变化的协同过滤推荐算法[J].计算机研究与发展,2007,44(2):296-301. 被引量:148
  • 3Resnick P, lakovou N, Sushak M, et al. GroupLens: An open architecture for collaborative filtering of netnews. Proc 1994 Computer Supported Cooperative Work Conf, Chapel Hill, 1994: 175-186
  • 4Hill W, Stead L, Rosenstein M, et al. Recommending and evaluating choices in a virtual community of use. Proc Conf Human Factors in Computing Systems. Denver, 1995:194 -201
  • 5梅田望夫.网络巨变元年-你必须参加的大未来.先觉:先觉出版社,2006
  • 6Adomavicius G, Tuzhilin A. Expert-driven validation of Rule Based User Models in personalization applications. Data Mining and Knowledge Discovery, 2001, 5(1-2):33-58
  • 7Adomavicius G, Tuzhilin A. Toward the next generation of recommender systems: A survey of the state-of-the art and possible extensions. IEEE Trans on Knowledge and Data Engineering, 2005, 17(6): 734-749
  • 8Rich E. User modeling via stereotypes. Cognitive Science, 1979, 3(4) : 329-354
  • 9Goldberg D, Nichols D, Oki BM, et al. Using collaborative filtering to weave an information tapestry. Comm ACM, 1992, 35(12):61-70
  • 10Konstan JA, Miller BN, Maltz D, el al. GroupLens: Applying collaborative filtering to usenet news. Comm ACM, 1997, 40(3) : 77-87

共引文献616

同被引文献157

引证文献11

二级引证文献11

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部