Design and development of a Personality Prediction System based on Mobile-Phone based Metrics

Alonso Aguilar, Carlos (2017). Design and development of a Personality Prediction System based on Mobile-Phone based Metrics. Proyecto Fin de Carrera / Trabajo Fin de Grado, E.T.S.I. Telecomunicación (UPM), Madrid.

Description

Title: Design and development of a Personality Prediction System based on Mobile-Phone based Metrics
Author/s:
  • Alonso Aguilar, Carlos
Contributor/s:
  • Iglesias Fernández, Carlos Ángel
Item Type: Final Project
Degree: Grado en Ingeniería de Tecnologías y Servicios de Telecomunicación
Date: 2017
Subjects:
Freetext Keywords: Machine Learning, Big Data, WhatsApp, Personality, Telecommunications.
Faculty: E.T.S.I. Telecomunicación (UPM)
Department: Ingeniería de Sistemas Telemáticos [hasta 2014]
Creative Commons Licenses: Recognition - No derivative works - Non commercial

Full text

[img]
Preview
PDF - Requires a PDF viewer, such as GSview, Xpdf or Adobe Acrobat Reader
Download (2MB) | Preview

Abstract

The need of communication between people is something that is associated in our nature as human beings, but the way people do it has completely changed since the smartphone and Internet appeared. Otherwise, knowing human personality of someone is something really difficult that we gain after working communication skills with others. Based on this two principal points in my TFG election, whose aim is predict human personality by recollecting information of smartphones, using Big Data and Machine Learning techniques. Firstly, we will proceed with a description of the diverse technologies utilized during the project's development for the manage of large quantities of data, and for the future automated process of supervised learning. After this, we will proceed with the study of the cases using data compiled from calls, messages, and geolocation, from which we will obtain the diverse characteristics that will later be compiled into the algorithms of the Machine Learning program. Three different systems will be designed using the features obtained from: calls, messages, and a combination of them both. On the other hand, communicational habits have shown a tremendous change since the polarization of smartphones. The use of calls has seen a steady decrease, while we progressively tend to ignore SMS's and communicate largely using instant messaging apps, like WhatsApp. For this reason, and with the objective of applying our models to the real world, the learning system created from SMS's to predict the user's personality will focus and use data entirely from WhatsApp conversations. In conclusion, this project has seen the development of three automated learning systems, with one of those previously mentioned applying data extracted from WhatsApp conversations. This has in turn lead to a greater percentage of success from the expected value, considering that there was no precedence in this area.

More information

Item ID: 47535
DC Identifier: http://oa.upm.es/47535/
OAI Identifier: oai:oa.upm.es:47535
Deposited by: Biblioteca ETSI Telecomunicación
Deposited on: 28 Aug 2017 10:49
Last Modified: 28 Aug 2017 10:49
  • Logo InvestigaM (UPM)
  • Logo GEOUP4
  • Logo Open Access
  • Open Access
  • Logo Sherpa/Romeo
    Check whether the anglo-saxon journal in which you have published an article allows you to also publish it under open access.
  • Logo Dulcinea
    Check whether the spanish journal in which you have published an article allows you to also publish it under open access.
  • Logo de Recolecta
  • Logo del Observatorio I+D+i UPM
  • Logo de OpenCourseWare UPM