|
Title:
|
A WEB RECOMMENDER SYSTEM BASED ON ANTCOLONY OPTIMIZATION |
|
Author(s):
|
Murat Göksedef , Gül Nildem Demir , Şule Gündüz Öğüdücü |
|
ISBN:
|
978-972-8924-40-9 |
|
Editors:
|
Jörg Roth, Jairo Gutiérrez and Ajith P. Abraham (series editors: Piet Kommers, Pedro Isaías and Nian-Shing Chen) |
|
Year:
|
2007 |
|
Edition:
|
Single |
|
Keywords:
|
Web mining, Recommender System, Ant Colony Optimization |
|
Type:
|
Full Paper |
|
First Page:
|
50 |
|
Last Page:
|
57 |
|
Language:
|
English |
|
Cover:
|
|
|
Full Contents:
|
click to dowload 
|
|
Paper Abstract:
|
The rapid growth of Internet has caused an increase in the amount of web pages. Even a small web site consists of
thousands of web pages and it becomes an important issue to guide the user to that contents she is or may be interested in.
Thus, predicting the interest of a user and using this information to make recommendations has gained importance.
Previously proposed methods for recommendation use data collected over time in order to recommend pages to new Web
users. However, they do not assess the recommendations made by the system to develop the system further. In this paper,
we present a new recommendation model for Web users which considers the behavior of new Web users. Our
recommendation model combines the Click-Stream Tree Model with a method that is inspired by the Ant Colony
Optimization method. Thus, our model is capable of learning new users behaviors. The experimental results show that
our model yields an improvement of the prediction accuracy. |
|
|
|
|
|
|
