The Set-up of Preprocessing Model of Web Site Web Log Data
Wei Peng · Enterprise Science and Technology & Development · 2010
The article studies the preprocessing of Web log data,and set up a general pre-processing model based on Web log data.The Web data pre-processing model mainly includes five steps:data cleaning,user identification,session identification, path supplement and formatting.Time dimension is added into the step of user identification,which improves the accuracy for user identification based on this calculation.After pre-processing,the semi-structured Web data is converted into structured data,which is helpful for Web mining at next step.Practice has proved that the model is feasible and good in expandability.