As the internet services are increasing day by day so various websites are working for webpage recommendation. Here researchers get new field for increasing the accuracy of the web page. This work has utilized web content feature of the website pages for developing the Term network where terms from each page help in specifying the relation between all pages. One more feature use in this work is web log where genetic algorithm named as ant colony model improved the prediction accuracy. Experiment is done on different dataset size for with thsese feature combination has shows that proposed modal is better as compare to previous work. Then, user navigational preferences, represented by pheromone levels, are directly proportional to the real frequency of usage.
So that the model presented in this work was a plausible way to integrate the ACO metaheuristic with web mining methodologies.Its multi-variable approach, which uses both content,structure and usage data from websources,allows the building of a framework for webusers imulation based on the construction of text preference vectors,whose fully parameterized structure allows the detection and in corporation of any change in web environment.
|IEEE Base Paper|
|Source Code||Complete Code files|