Please use this identifier to cite or link to this item: http://hdl.handle.net/10609/119206
Title: Ús d'algorismes genètics per desxifrar algorismes de classificació opacs
Author: Llabrés Darder, Albert
Tutor: Pérez Rosés, Hebert
Abstract: In recent years, the media has become a key element in conveying information in a certain way with the aim of creating a concrete opinion in the reader.Traditionally, this goal has been achieved through the writing of the information itself. However, with the advent of interactive products where all users can exchange information, it has become key how these users transmit this information as well as the positioning they obtain. During this master's thesis, the news published in Yahoo!News has been trackedin order to arrive at an approximation in their comment classification algorithms.The aim of this work is to be able to understand which parameters are more important when establishing the order in which end users will receive the published comments, so that the entities interested in this aspect can write comments in a way efficient with the aim of transmitting certain information.In order to achieve this goal, in this work we have used methodologies studied in this master's degree, such as meta-heuristic optimization algorithms, genetic programming, symbolic regressions, etc.The results of this work will provide an approximation to the ranking algorithms used by Yahoo!News, so that we can deduce the criteria followed witha certain relative error.The conclusions of this work will allow us to verify that Yahoo!News makes use of classification parameters that are not available to its users, and therefore has a high opacity.
Keywords: applied mathematics
genetic algorithms
symbolic regression
Document type: info:eu-repo/semantics/masterThesis
Issue Date: 21-Jun-2020
Publication license: http://creativecommons.org/licenses/by-nc-nd/3.0/es/  
Appears in Collections:Treballs finals de carrera, treballs de recerca, etc.

Files in This Item:
File Description SizeFormat 
Dump20200625.rar49,97 MBWinRarView/Open
plotMessageTrace.m1,52 kBMatlab scriptView/Open
tracings.rar31,1 kBWinRarView/Open
YahooNews.rar42,35 MBWinRarView/Open
albertllabresTFM0620memoria.pdfMemoria del TFM1,46 MBAdobe PDFThumbnail
View/Open