Εισηγητικά συστήματα και προστασία προσωπικών δεδομένων

Καλέμου, Δήμητρα

Recommendation system and privacy policies

Master Thesis

Author

Καλέμου, Δήμητρα

Date

2015-04

View/Open

Μεταπτυχιακή εργασία (14.71Mb)

Subject

Δεδομένα -- Προστασία ; Διαδίκτυο (Internet) -- Μέτρα ασφαλείας ; Data protection ; Recommender systems (Information filtering) ; Internet (Computer network) -- Security measures

Abstract

The aim of the thesis is the study of Internet Recommendation Systems that are based on user preferences modeling and on information filtering, and the implementation of an application, as well. Last years there is a lot of speculation among the members of the community of artificial intelligence concerning the way AI can help with the problem of successful information search in the reservoirs of knowledge of Internet. Recommendation systems provide a solution in this problem giving individualized recommendations. The successful generation, maintenance and exploitation of single user profiles are proved particularly critical dimensions in order to achieve individualization. That is why the presentation of a classification and short analysis of these dimensions is considered to be useful. In the thesis are presented the methods of content-based and collaborative filtering and hybrid recommendation systems. The study provides important in the protection of the users and the personal data and it is completed with the presentation of a Recommendation System model that emphasizes in the user's anonymity.