Mena, JoséVitrià i Marca, JordiCardús García, Marc2019-06-042019-06-042018-09-26https://hdl.handle.net/2445/134477Treballs finals del Màster de Fonaments de Ciència de Dades, Facultat de matemàtiques, Universitat de Barcelona, Any: 2018, Tutor: José Mena i Jordi Vitrià i Marca[en] Imagine you are reading a newspaper, a blog, a scientific publication or a forum and you have become interested in a certain topic. After reading that site you may want to know more about it, so you click in a button and GuruFinder propose you a list of Twitter users to follow experts on that topic. The concept may be easy but the technology required underneath implies the combination of different disciplines including natural language processing, recommender systems, text mining, knowledge management systems and big data processing. GuruFinders pretends to explore state of the art techniques to build a prototype able to handle and process big volumes of tweets and offer real-time responses to the users.50 p.application/pdfengcc-by-nc-nd (c) Marc Cardús Garcia, 2018codi: GPL (c) Marc Cardús Garcia, 2018http://creativecommons.org/licenses/by-nc-nd/3.0/es/http://www.gnu.org/licenses/gpl-3.0.ca.htmlTractament del llenguatge natural (Informàtica)Sistemes d'ajuda a la decisióTreballs de fi de màsterDades massivesTwitterXarxes socials en líniaNatural language processing (Computer science)Decision support systemsMaster's thesesBig dataOnline social networksinfo:eu-repo/semantics/masterThesisinfo:eu-repo/semantics/openAccess