Urruticoechea, EduardoPlanes Vivancos, Ricard2022-01-272022-01-272021-06-19https://hdl.handle.net/2445/182700Treballs Finals de Grau d'Enginyeria Informàtica, Facultat de Matemàtiques, Universitat de Barcelona, Any: 2021, Director: Eduardo Urruticoechea[en] The aim of this project is to implement an unsupervised, fast and low-cost machine learning algorithm capable of identifying the sentiment conveyed by each tweet from a set of tweets in order to calculate the percentage of those positive and negative. To do this, we will also create the Dataset of tweets to classify with which the algorithm will be trained. This project intends to be useful to those companies that during an advertising campaign are looking for a quick first analysis of the catalan-speaking users’ acceptance on Twitter.45 p.application/pdfcatmemòria: cc-nc-nd (c) Ricard Planes Vivancos, 2021codi: GPL (c) Ricard Planes Vivancos, 2021http://creativecommons.org/licenses/by-nc-nd/3.0/es/http://www.gnu.org/licenses/gpl-3.0.ca.htmlXarxes socialsAprenentatge automàticProgramariTreballs de fi de grauSistemes classificadors (Intel·ligència artificial)Algorismes computacionalsReputació en líniaEmocionsSocial networksMachine learningComputer softwareLearning classifier systemsComputer algorithmsBachelor's thesesReputation managementEmotionsinfo:eu-repo/semantics/bachelorThesisinfo:eu-repo/semantics/openAccess