Survey on Pre-Processing Web Log Files in Web Usage Mining

EasyChair Preprint 1927

Abstract

Web mining is to decide and extricate helpful data. In the web age, web applications are expanding at gigantic speed and the web clients are expanding at exponential speed.  the number of clients develops, site distributers are having expanding their data for pulling in and fulfilling clients. It is conceivable to follow the clients' quintessence and collaborations with web applications through web server log record and Weblog document contains just (.txt) record. The information put away in the weblog record comprises of enormous measures of disintegrated, inadequate, and pointless data. In view of the enormous measure of superfluous information accessible in the weblog record, a unique log document can't be straightforwardly utilized in the web use mining. So pre-processing method is connected to improve the quality and effectiveness of a weblog record. Various procedures are connected in pre-processing that is information cleaning, information combination, information join. In this paper, we will overview a distinctive pre-processing system to recognize the issues in weblog documents and to improve web utilization digging pre-processing for example mining and investigation.

KEYWORDS: data cleaning, data fusion, data integration, Pre-processing technique, Web usage mining, weblog file

Keyphrases: data cleaning, data fusion, data integration

@booklet{EasyChair:1927,
  author    = {Rita Roy and Apparao Giduturi},
  title     = {Survey on Pre-Processing Web Log Files in Web Usage Mining},
  howpublished = {EasyChair Preprint 1927},
  year      = {EasyChair, 2019}}