Applying sentiment analysis for detection of cyberbullying in Twitter
View/Open
143355.pdf (1,147Mb) (Restricted access)
Cita com:
hdl:2117/364240
Tutor / directorFranqueira, Virginia
CovenanteeUniversity of Derby
Document typeBachelor thesis
Date2019-05-31
Rights accessRestricted access - author's decision
All rights reserved. This work is protected by the corresponding intellectual and industrial
property rights. Without prejudice to any existing legal exemptions, reproduction, distribution, public
communication or transformation of this work are prohibited without permission of the copyright holder
Abstract
El proyecto pretende comparar técnicas de Sentiment Analysis para detectar contenido dañino en tweets extraídos de Twitter usando R. Se aplican tres técnicas supervisadas de machine learning: SVM lineal, SVM kernel y Naive Bayes. El algoritmo que obtiene la mayor exactitud es SVM kernel.
DegreeGRAU EN ENGINYERIA INFORMÀTICA (Pla 2010)
Collections
Files | Description | Size | Format | View |
---|---|---|---|---|
143355.pdf | 1,147Mb | Restricted access |