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.

Descripción

Título: Design and development of a Personality Prediction System based on Mobile-Phone based Metrics
Autor/es:
  • Alonso Aguilar, Carlos
Director/es:
  • Iglesias Fernández, Carlos Ángel
Tipo de Documento: Proyecto Fin de Carrera/Grado
Grado: Grado en Ingeniería de Tecnologías y Servicios de Telecomunicación
Fecha: 2017
Materias:
Palabras Clave Informales: Machine Learning, Big Data, WhatsApp, Personality, Telecommunications.
Escuela: E.T.S.I. Telecomunicación (UPM)
Departamento: Ingeniería de Sistemas Telemáticos [hasta 2014]
Licencias Creative Commons: Reconocimiento - Sin obra derivada - No comercial

Texto completo

[img]
Vista Previa
PDF (Document Portable Format) - Se necesita un visor de ficheros PDF, como GSview, Xpdf o Adobe Acrobat Reader
Descargar (2MB) | Vista Previa

Resumen

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.

Más información

ID de Registro: 47535
Identificador DC: http://oa.upm.es/47535/
Identificador OAI: oai:oa.upm.es:47535
Depositado por: Biblioteca ETSI Telecomunicación
Depositado el: 28 Ago 2017 10:49
Ultima Modificación: 28 Ago 2017 10:49
  • Open Access
  • Open Access
  • Sherpa-Romeo
    Compruebe si la revista anglosajona en la que ha publicado un artículo permite también su publicación en abierto.
  • Dulcinea
    Compruebe si la revista española en la que ha publicado un artículo permite también su publicación en abierto.
  • Recolecta
  • e-ciencia
  • Observatorio I+D+i UPM
  • OpenCourseWare UPM