Ευφυές, προσαρμοστικό σύστημα πολλών πρακτόρων για τη συλλογή πληροφοριών από το διαδίκτυο
An intelligent and adaptive multiagent system for information collection from the internet
In this thesis we consider the problem of building intelligent agents to facilitate a person's search for information on the web. We have developed webnaut, an intelligent multiagent system that uses a meta-genetic algorithm, in order to collect and recommend web pages that will be interesting to the user. The user's feedback on agent's recommendations drives the learning process to adapt the user's profile with his/her interests. The system autonomously uses the web's search engines so as to discover and recommend new documents that are relevant to the documents, which the user has indicated that interest him/her. Experiments have been applied to a group of users so that we can evaluate the efficiency and the system's ability to learn.