Please use this identifier to cite or link to this item:
Title: An empirical study of trope-based recommendation systems for animes
Authors: Brito, Ana Caroline Medeiros
Keywords: Recommender Systems;Hybrid Systems;Tropes;Japanese animation
Issue Date: 27-Nov-2018
Publisher: Universidade Federal do Rio Grande do Norte
Citation: BRITO, Ana Caroline Medeiros. An empirical study of trope-based recommendation systems for animes. 2018. 55 f. Trabalho de Conclusão de Curso (Bacharelado em Ciência da Computação) - Universidade Federal do Rio Grande do Norte, Natal, 2018.
Portuguese Abstract: Recommender Systems is a fundamental field of study considering the big volume of information and data available everywhere - when we need to choose something to buy, to use, to experience. These systems have the purpose of help users in the task of choosing or even just suggesting some services. This work is an overview of the main approaches used to make a recommendation and an investigation about how features present in stories - called tropes - can be helpful to increase prediction quality. There were tested seven algorithms, two of them using tropes. We have tested said algorithms with a new database composed of Japanese animations and tropes that is also a contribution of this work. Some interesting conclusions were obtained analyzing the results in the new database proposed and the other one already known - MovieLens enriched with tropes -, the testes with tropes disclose no substantial positive impact in predictions
Other Identifiers: 20170153888
Appears in Collections:Ciência da Computação

Files in This Item:
File Description SizeFormat 
AnEmpiricalStudyAnimes_Brito_2018.pdf453,72 kBAdobe PDFThumbnail

This item is licensed under a Creative Commons License Creative Commons