The Online Social Self: An Open Vocabulary Approach to Personality

Margaret L. Kern; Johannes C. Eichstaedt; H. Andrew Schwartz; Lukasz Dziurzynski; Lyle H. Ungar; David J. Stillwell; Michal Kosinski; Stephanie M. Ramones; Martin E.P. Seligman

doi:10.1177/1073191113514104

The Online Social Self: An Open Vocabulary Approach to Personality

Margaret L. Kern
, Johannes C. Eichstaedt
, H. Andrew Schwartz
, Lukasz Dziurzynski
, Lyle H. Ungar
, David J. Stillwell
, Michal Kosinski
, Stephanie M. Ramones
, Martin E.P. Seligman

Computer Science

Stony Brook University

University of Pennsylvania
University of Cambridge

Research output: Contribution to journal › Article › peer-review

111 Scopus citations

Abstract

Objective: We present a new open language analysis approach that identifies and visually summarizes the dominant naturally occurring words and phrases that most distinguished each Big Five personality trait. Method: Using millions of posts from 69,792 Facebook users, we examined the correlation of personality traits with online word usage. Our analysis method consists of feature extraction, correlational analysis, and visualization. Results: The distinguishing words and phrases were face valid and provide insight into processes that underlie the Big Five traits. Conclusion: Open-ended data driven exploration of large datasets combined with established psychological theory and measures offers new tools to further understand the human psyche.

Original language	English
Pages (from-to)	158-169
Number of pages	12
Journal	Assessment
Volume	21
Issue number	2
DOIs	https://doi.org/10.1177/1073191113514104
State	Published - Apr 2014

Keywords

Big Five personality
computational social science
interdisciplinary research
linguistic analysis
online studies

Access to Document

10.1177/1073191113514104

Cite this

@article{4e6539d38b274dd9ba3cd1b07ba741ab,

title = "The Online Social Self: An Open Vocabulary Approach to Personality",

abstract = "Objective: We present a new open language analysis approach that identifies and visually summarizes the dominant naturally occurring words and phrases that most distinguished each Big Five personality trait. Method: Using millions of posts from 69,792 Facebook users, we examined the correlation of personality traits with online word usage. Our analysis method consists of feature extraction, correlational analysis, and visualization. Results: The distinguishing words and phrases were face valid and provide insight into processes that underlie the Big Five traits. Conclusion: Open-ended data driven exploration of large datasets combined with established psychological theory and measures offers new tools to further understand the human psyche.",

keywords = "Big Five personality, computational social science, interdisciplinary research, linguistic analysis, online studies",

author = "Kern, \{Margaret L.\} and Eichstaedt, \{Johannes C.\} and Schwartz, \{H. Andrew\} and Lukasz Dziurzynski and Ungar, \{Lyle H.\} and Stillwell, \{David J.\} and Michal Kosinski and Ramones, \{Stephanie M.\} and Seligman, \{Martin E.P.\}",

year = "2014",

month = apr,

doi = "10.1177/1073191113514104",

language = "English",

volume = "21",

pages = "158--169",

journal = "Assessment",

issn = "1073-1911",

publisher = "SAGE Publications Inc.",

number = "2",

}

TY - JOUR

T1 - The Online Social Self

T2 - An Open Vocabulary Approach to Personality

AU - Kern, Margaret L.

AU - Eichstaedt, Johannes C.

AU - Schwartz, H. Andrew

AU - Dziurzynski, Lukasz

AU - Ungar, Lyle H.

AU - Stillwell, David J.

AU - Kosinski, Michal

AU - Ramones, Stephanie M.

AU - Seligman, Martin E.P.

PY - 2014/4

Y1 - 2014/4

N2 - Objective: We present a new open language analysis approach that identifies and visually summarizes the dominant naturally occurring words and phrases that most distinguished each Big Five personality trait. Method: Using millions of posts from 69,792 Facebook users, we examined the correlation of personality traits with online word usage. Our analysis method consists of feature extraction, correlational analysis, and visualization. Results: The distinguishing words and phrases were face valid and provide insight into processes that underlie the Big Five traits. Conclusion: Open-ended data driven exploration of large datasets combined with established psychological theory and measures offers new tools to further understand the human psyche.

AB - Objective: We present a new open language analysis approach that identifies and visually summarizes the dominant naturally occurring words and phrases that most distinguished each Big Five personality trait. Method: Using millions of posts from 69,792 Facebook users, we examined the correlation of personality traits with online word usage. Our analysis method consists of feature extraction, correlational analysis, and visualization. Results: The distinguishing words and phrases were face valid and provide insight into processes that underlie the Big Five traits. Conclusion: Open-ended data driven exploration of large datasets combined with established psychological theory and measures offers new tools to further understand the human psyche.

KW - Big Five personality

KW - computational social science

KW - interdisciplinary research

KW - linguistic analysis

KW - online studies

UR - https://www.scopus.com/pages/publications/84900401551

U2 - 10.1177/1073191113514104

DO - 10.1177/1073191113514104

M3 - Article

C2 - 24322010

SN - 1073-1911

VL - 21

SP - 158

EP - 169

JO - Assessment

JF - Assessment

IS - 2

ER -

The Online Social Self: An Open Vocabulary Approach to Personality

Abstract

Keywords

Access to Document

Other files and links

Fingerprint

Cite this