Predicting Personality Using Novel Mobile Phone-Based Metrics

  • Yves-Alexandre de Montjoye
  • Jordi Quoidbach
  • Florent Robic
  • Alex (Sandy) Pentland
Conference paper

DOI: 10.1007/978-3-642-37210-0_6

Part of the Lecture Notes in Computer Science book series (LNCS, volume 7812)
Cite this paper as:
de Montjoye YA., Quoidbach J., Robic F., Pentland A.. (2013) Predicting Personality Using Novel Mobile Phone-Based Metrics. In: Greenberg A.M., Kennedy W.G., Bos N.D. (eds) Social Computing, Behavioral-Cultural Modeling and Prediction. SBP 2013. Lecture Notes in Computer Science, vol 7812. Springer, Berlin, Heidelberg

Abstract

The present study provides the first evidence that personality can be reliably predicted from standard mobile phone logs. Using a set of novel psychology-informed indicators that can be computed from data available to all carriers, we were able to predict users’ personality with a mean accuracy across traits of 42% better than random, reaching up to 61% accuracy on a three-class problem. Given the fast growing number of mobile phone subscription and availability of phone logs to researchers, our new personality indicators open the door to exciting avenues for future research in social sciences. They potentially enable cost-effective, questionnaire-free investigation of personality-related questions at a scale never seen before.

Keywords

Personality prediction Big Data Big Five Personality prediction Carrier’s log CDR 

Preview

Unable to display preview. Download preview PDF.

Unable to display preview. Download preview PDF.

Copyright information

© Springer-Verlag Berlin Heidelberg 2013

Authors and Affiliations

  • Yves-Alexandre de Montjoye
    • 1
  • Jordi Quoidbach
    • 2
  • Florent Robic
    • 3
  • Alex (Sandy) Pentland
    • 1
  1. 1.The Media LaboratoryMassachusetts Institute of TechnologyCambridgeUSA
  2. 2.Department of PsychologyHarvard UniversityCambridgeUSA
  3. 3.Ecole Normale Supérieure de LyonLyonFrance

Personalised recommendations