Issue No. 02 - March/April (2004 vol. 19)
Doru Tanasa , AxIS Project Team, Inria
Brigitte Trousse , AxIS Project Team, INRIA Sophia Antipolis
<p>In recent years, Web usage mining has emerged as a new field of data mining and gained increasing attention from both the business and research communities. A particular area of importance is data preprocessing for Intersites WUM. The proposed methodology for this process has two main objectives. The first is to use classical preprocessing (data fusion, data cleaning, and data structuration) to significantly reduce, but in a relevant manner, the size of the Web servers? log files. The second is to use advanced data preprocessing, which employs an extra step called data summarization to increase the quality of data obtained after classical preprocessing. To validate this methodology?s efficiency, an experiment joined and analyzed log files from four related servers.</p>
data mining, Web mining, traffic analysis, Web site management, Web usage mining, KDD, data preparation, user session
B. Trousse and D. Tanasa, "Advanced Data Preprocessing for Intersites Web Usage Mining," in IEEE Intelligent Systems, vol. 19, no. , pp. 59-65, 2004.