Recomendação de Percursos Culturais com Escassez de Dados

• Main Author: Maria Inês Fontes Rocha
• Publication Date: 2018
• Format: Master thesis
• Language: por
• Source: Repositórios Científicos de Acesso Aberto de Portugal (RCAAP)
• Download full: https://repositorio-aberto.up.pt/handle/10216/114056
• topic: Ciências da computação e da informação; Computer and information sciences

The exchange of historical, cultural and scientific heritage is nowadays accessible to global peoples thanks to information and communication technologies. Porto's University project Museu Digital da Universidade do Porto aims to share its assets with the different community's trough digital means. This method to share knowledge can be sometimes eased through recommender systems. The main purpose of a recommender system is to suggest items to a user according to its needs and preferences. This thesis implements a recommender system in which the main purpose is to share the Porto's University assets, highlighting points of interest. The early stage of the project Museu Digital da Universidade do Porto was the main obstacle of this thesis, due to the lack of user's data. Therefore, this thesis presents a recommender system based on sequential data mining algorithm SPADE which suggests points of interest as a sequence. This is an exploratory work able to be adapted to the possible development of the project, with new points of interest data, the record of historical visit data and user profile data.Keywords: recommender system, sequence pattern mining, point of interest (POI), spade