摘要
提出一种基于协同过滤的网络论坛个性化推荐算法,根据用户的发帖、回帖、阅读等记录,采用加权方法计算用户帖子的评分矩阵,获取邻近用户集合,通过邻居用户的帖子评分,计算目标用户的帖子预测评分,推荐预测评分最高的帖子。实验结果表明,该算法的推荐质量较高。
This paper proposes a personalized recommendation algorithm of Internet forum based on collaborative filtering.According to the users posting,replies,and reading records,it computes user rating matrix by weighted method,gets the nearest users,then calculates the target user＇s posts prediction score according to neighbors＇ posts,and recommends the highest score prediction posts to target user.Experimental results show that the algorithm can recommend high-quality posts.
出处
《计算机工程》
CAS
CSCD
2012年第5期67-69,共3页
Computer Engineering
基金
国家自然科学基金资助项目(61070061)
关键词
网络论坛
个性化推荐
协同过滤
相似度
用户兴趣
Internet forum
personalized recommendation
collaborative filtering
similarity
user interest
