Web日志挖掘

Research on Weblog mining

提出了一种新颖的MBP算法 ,它利用关联规则挖掘发现的频繁项目集以加快速度 ,能找出所有满足阀值约束的频繁浏览路径 ,该算法是很有效的 .同时 ,针对Web浏览和日志文件固有的模糊性和不确定性 ,还讨论了Web页面的模糊聚类问题 .最后 。

Similar customer groups, relevant Web pages, and frequent access paths can be discovered by mining Weblog files. Based on a survey of current Web mining research, an algorithm of MBP is presented. It uses frequent items found during association rules mining. MBP can find all frequent access paths meeting threshold constraint. Experiment shows that MBP algorithm is very effective. At the same time, due to the inherent fuzziness and uncertainty in Web browsing and logging, fuzzy clustering for Web pages is also discussed. Finally a discussion concerning the use of discovered knowledge in recommendation system and adaptive Web site as well as some algorithm methods are also given.