摘要
随着网络信息资源的迅速增加,如何及时准确地获取所需信息是现代网络信息过滤技术需要解决的主要问题。为了给用户提供更准确的信息,提出了一种基于用户反馈的智能合作过滤模型(Agent collaborative filtering model based on users' feedback,ACFM)和用户兴趣模型,该模型通过隐式反馈和显式反馈这两种用户兴趣反馈学习实现合作过滤。实验结果表明,ACFM在预测用户兴趣的效果和推荐搜索信息的准确率方面比传统的搜索引擎有明显改善。
With the increasing of web information, how to filter information which users wanted quickly and accurately is becoming a big business. In order to serve users the more accurate information, the Agent collaborative filtering model based on users＇ feedback, ACFM and users＇ interesting model are put forward. ACFM uses the learning method of users＇ interesting feedback consisted of implicit feedback and interactive feedback to realize collaborative filtering. Experimental results show that compared with the traditional search tool, ACFM has more effective on deducing users＇ interesting and more accuracy in recommending information.
出处
《计算机工程与设计》
CSCD
北大核心
2007年第7期1659-1662,共4页
Computer Engineering and Design
基金
国家自然科学基金项目(60473039)
江苏大学教改基金项目。
关键词
合作过滤
AGENT
用户兴趣
机器学习
共同兴趣模型
collaborative filtering
Agent
users＇ interesting feedback
machine learning
co-model
