A vectorial semantics approach to personality assessment

Yair Neuman, Yochai Cohen

Research output: Contribution to journalArticlepeer-review

20 Scopus citations

Abstract

Personality assessment and, specifically, the assessment of personality disorders have traditionally been indifferent to computational models. Computational personality is a new field that involves the automatic classification of individuals' personality traits that can be compared against gold-standard labels. In this context, we introduce a new vectorial semantics approach to personality assessment, which involves the construction of vectors representing personality dimensions and disorders, and the automatic measurements of the similarity between these vectors and texts written by human subjects. We evaluated our approach by using a corpus of 2468 essays written by students who were also assessed through the five-factor personality model. To validate our approach, we measured the similarity between the essays and the personality vectors to produce personality disorder scores. These scores and their correspondence with the subjects' classification of the five personality factors reproduce patterns well-documented in the psychological literature. In addition, we show that, based on the personality vectors, we can predict each of the five personality factors with high accuracy.

Original languageEnglish
Article number4761
JournalScientific Reports
Volume4
DOIs
StatePublished - 23 Apr 2014

Fingerprint

Dive into the research topics of 'A vectorial semantics approach to personality assessment'. Together they form a unique fingerprint.

Cite this