M.Sc., Mining Client Side Para-data for Adaptive Web Pages, Jordan University of Science and Technology , Jordan.
| Type of publication: | Misc |
| Citation: | M.Sc. |
| Year: | 2011 |
| Abstract: | In this thesis, we propose a complete framework that customizes web pages to improve clients experience while browsing web pages. We use client-side scripting to track user behaviors. Client-side scripting tracks all interactions and events such as click events. Discovering interactions between clients and visited websites based on clients' data could help understand and satisfy clients' needs. Unfortunately, until now there is no complete framework which could record and mine in the clients' data. Thus, the main contribution of this thesis is to build a complete framework that can recode clients' events and apply the Web Usage Mining techniques on this data. We show the usefulness of the clients' data. Additionally, we filter and process the clients' data and then we apply WUM techniques on it. To validate the proposed framework, we build three different web applications and then we integrate our framework with them. We build a recommendation engine, which is able to discover the clients' patterns. Moreover, we extract the useful information from the clients' data. However, clients' data model based on clients' data statistics is generated. Finally, our framework enjoys high accuracy rate in the classification methods, which is around 90%. |
| Userfields: | pdfurl={http://cosy.informatik.uni-bremen.de/sites/default/files/Rami_WebMining_Final_thesis.pdf}, project={cosy}, status={Reviewed}, |
| Keywords: | Data Mining, Web mining |
| Authors | |
|
Attachments
|
|
|
|
|
Notes
|
|
|
|
|
|
Topics
|
|
|
|
