Computational Personality Assessment

Authors

  • Clemens Stachl Orcid
    Department of Communication, Stanford University, Stanford, CA, USA
  • Ryan L. Boyd Orcid
    Department of Psychology, Lancaster University, Lancaster, United Kingdom; Security Lancaster, Lancaster University, Lancaster, United Kingdom; Data Science Institute, Lancaster University, Lancaster, United Kingdom
  • Kai T. Horstmann Orcid
    Institute of Psychology, Humboldt-University of Berlin, Berlin, Germany
  • Poruz Khambatta Orcid
    Anderson School of Management, UCLA, Los Angeles, CA, USA
  • Sandra C. Matz Orcid
    Columbia Business School, Columbia University, New York City, NY, USA
  • Gabriella M. Harari Orcid
    Department of Communication, Stanford University, Stanford, CA, USA

Abstract

Computational methods have increased the objectivity of measures of human behavior and positioned personality science to benefit from the ongoing digital revolution. In this review, we define and discuss computational personality assessment (CPA), a measurement process that uses computational technologies to obtain estimates of personality. We briefly review some of the most promising sources of data currently used for CPA: mobile sensing, digital footprints from social media, images, language, and experience sampling. We present a concise overview of key findings, discuss the promise and opportunities of CPA (e.g., moving towards objective measures of personality, obtaining new insights from big data), and highlight important limitations and challenges in the development and application of CPA (e.g., establishing reliability and validity, selecting appropriate ground truth criterion, assessing affect and cognition, implications for ethics and privacy). We conclude with our perspective on how CPA could change our understanding of individual differences.