A Constraint Programming Approach for Web Log Mining

A Constraint Programming Approach for Web Log Mining

Amina Kemmar (LITIO, University of Oran 1, Ahmed Ben Bella, Oran, Algeria), Yahia Lebbah (LITIO, University of Oran 1, Ahmed Ben Bella, Oran, Algeria) and Samir Loudni (GREYC (CNRS UMR 6072), University of Caen, Caen, France)
DOI: 10.4018/IJITWE.2016100102
OnDemand PDF Download:
$30.00
List Price: $37.50

Abstract

Mining web access patterns consists in extracting knowledge from server log files. This problem is represented as a sequential pattern mining problem (SPM) which allows to extract patterns which are sequences of accesses that occur frequently in the web log file. There are in the literature many efficient algorithms to solve SMP (e.g., GSP, SPADE, PrefixSpan, WAP-tree, LAPIN, PLWAP). Despite the effectiveness of these methods, they do not allow to express and to handle new constraints defined on patterns, new implementations are required. Recently, many approaches based on constraint programming (CP) was proposed to solve SPM in a declarative and generic way. Since no CP-based approach was applied for mining web access patterns, the authors introduce in this paper an efficient CP-based approach for solving the web log mining problem. They bring back the problem of web log mining to SPM within a CP environment which enables to handle various constraints. Experimental results on non-trivial web log mining problems show the effectiveness of the authors' CP-based mining approach.
Article Preview

1. Introduction

Sequential pattern mining (SPM) is a well-known data mining technique introduced in (Srikant & Agrawal, 1995) to find regularities in a database of sequences. With the increasing amount of data available on the World Wide Web (WWW), discovering and analyzing useful information from the WWW becomes an essential task (Blockeel & Kosala, 2000). The task of Web Mining consists to extract an interesting and potentially meaningful patterns based on activities related to the WWW (Kohavi, 2002). There are roughly three knowledge discovery domains that pertain to web mining (Cooley, 1997): web content mining, web structure mining and web usage mining. In Web Usage Mining (WUM), also known as web access, the mining process aims at extracting knowledge from server log files collected when users access Web servers over a period of time (Kohavi, 2002).

Mining web access patterns from Web logs can provide useful information for server performance enhancements, restructuring a web site, and direct marketing in e-commerce (Etzioni & Oren, 1996). For an e-commerce company, this may help detecting future customers likely to make a large number of purchases, or predicting which online visitors will click on what commercials or banners, based on observation of prior visitors, who have behaved both positively or negatively to the advertisement banner (Ezeife & Yi, 2005).

There are already in the literature many efficient algorithms to extract sequential patterns (e.g. GSP (Agrawal & Srikant, 1996), SPADE (Zaki, 2001), PrefixSpan (Pei, Han, Mortazavi-Asl, Pinto, Dayal, & Hsu, 2001), web sequential patterns on web log data (e.g. WAP-tree (Jian Pei J. H.-A., 2000)), PLWAP (Ezeife & Yi, 2005)), closed sequential patterns (e.g. CloSpan (Yan, Han, & Afshar, 2003), BIDE (Han & Wang, 2004)) or sequential patterns satisfying regular expressions (e.g. SPIRIT (Minos, Garofalakis, & Rastogi, 2002)). All the above methods, though efficient, they suffer from two major problems. First, they tackle particular classes of constraints (i.e. monotonic1 and anti-monotonic ones (see Section 5.3)) by using devoted techniques. However, several practical constraints required in data mining tasks, such as regular expression, gap, aggregates, do not fit into these classes. Second, they suffer from a lack of genericity to handle simultaneously different types of constraints in a simple way. Indeed, new constraints have to be hand-coded and their combinations often require the revision of the original algorithm to take into account the new constraints.

Complete Article List

Search this Journal:
Reset
Open Access Articles: Forthcoming
Volume 13: 4 Issues (2018): 1 Released, 3 Forthcoming
Volume 12: 4 Issues (2017)
Volume 11: 4 Issues (2016)
Volume 10: 4 Issues (2015)
Volume 9: 4 Issues (2014)
Volume 8: 4 Issues (2013)
Volume 7: 4 Issues (2012)
Volume 6: 4 Issues (2011)
Volume 5: 4 Issues (2010)
Volume 4: 4 Issues (2009)
Volume 3: 4 Issues (2008)
Volume 2: 4 Issues (2007)
Volume 1: 4 Issues (2006)
View Complete Journal Contents Listing