User traversal behaviour mining of server logs using fuzzy FRS /
Web Usage Mining (WUM) is the application of data mining methods in extracting potentially useful information from web usage data. Its application includes improving website design, personalised service, target marketing etc. Even though there has been an extensive study in WUM, lack of related prod...
Saved in:
| Main Author: | |
|---|---|
| Format: | Thesis |
| Language: | English |
| Published: |
Kuala Lumpur :
KUlliyyah of Information and Communication Technology, International Islamic University Malaysia,
2018
|
| Subjects: | |
| Online Access: | Click here to view 1st 24 pages of the thesis. Members can view fulltext at the specified PCs in the library. |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Web Usage Mining (WUM) is the application of data mining methods in extracting potentially useful information from web usage data. Its application includes improving website design, personalised service, target marketing etc. Even though there has been an extensive study in WUM, lack of related product commercialisation indicates that there are still a number of outstanding research issues in this area. Among the challenges mentioned in the literature include inefficiency in mining typically large weblogs, extracted patterns that are not representative of actual user behavior, and mining results which are too general, uninteresting and lack insights. This thesis attempts to address the above problems in three parts. Firstly, based on the notion of regularity, a mining algorithm is introduced to efficiently extract usage patterns from large weblogs that are reflective of individual user behaviour. Secondly, a fuzzy method is incorporated into the algorithm that enables the expression of the pattern quality, thus reducing possible confusion due to extremely large number of patterns. Finally, in order to gain deeper insights of the extracted patterns, the algorithm is further extended using the framework of transitional pattern to capture possible variation in pattern behaviour, thus facilitating the subsequent pattern interpretation process. The promising results obtained from a series of experiments conducted suggest that the new algorithm is faster and more scalable compared to an existing one, especially when mining large weblogs. Furthermore, the extracted patterns demonstrate better representation of user traversal behaviour, contain less ambiguity, and are more readily interpretable for subsequent analysis. |
|---|---|
| Physical Description: | xiv, 168 leaves : illustrations ; 30cm. |
| Bibliography: | Includes bibliographical references (leaves 128-136). |