The 50/50 recommender: personality in movie recommender systems

 
This item is provided by the institution :

Repository :
IHU Repository
see the original item page
in the repository's web site and access all digital files if the item*
share




2017 (EN)
The 50/50 recommender: personality in movie recommender systems (EN)

Nalmpantis, Orestis (EN)

School of Science and Technology, MSc in Information & Communication Technology Systems (EL)
Berberidis, Christos (EN)
Basilliades, Nick (EN)
Tjortjis, Chistos (EN)

This dissertation was written as a part of the MSc in ICT Systems at the International Hellenic University. Its main goal is the examination of the role of human personality in Movie Recommender systems. We introduce the concept of combining collaborative techniques with a personality test so to provide more personalized movie recommendations. Previous research has shown some efforts to incorporate personality in Recommender systems, but no actual implementation has been attempted on a software level. Using a renowned movie dataset and the Big Five Personality test, we developed a system with Python that managed to improve the normal Movie Recommendation experience by 3.62%. The findings show that Personalization improves the user’s experience even though extra effort might be demanded. With further modifications and testing, we can come to the new age of recommender systems, where personality of the user is as important as it is in real life. (EN)

masterThesis

Διεθνές Πανεπιστήμιο της Ελλάδος (EL)
International Hellenic University (EN)

2017-01-01


IHU (EN)



*Institutions are responsible for keeping their URLs functional (digital file, item page in repository site)