A Rough Sets Based Data Preprocessing Algorithm for Web Structure Mining

摘要

Aimed to enhance the efficiency of web structure mining, based on the Rough Sets (RS), an effective web structure mining preprocessing algorithm is proposed in this paper. Firstly, to linear the huge web link graph, the Vast Forward Path (VFP) is introduced and extracted from the user access record in web server logs. Secondly, to build the data analysis model, the Information System is constructed using the VFP. Thirdly, the paper make using of the attribute reduction theory of RS; the Information System is reduced by eliminate a lot of abundant attributes. The experiments show that the proposed algorithm can get high efficiency and avoid the abundant web redundant data.