Am I who I say I am? Unobtrusive self-representation and personality recognition on Facebook

Margaret A Hall, Simon Caton

Research output: Contribution to journalArticle

5 Citations (Scopus)

Abstract

Across social media platforms users (sub)consciously represent themselves in a way which is appropriate for their intended audience. This has unknown impacts on studies with unobtrusive designs based on digital (social) platforms, and studies of contemporary social phenomena in online settings. A lack of appropriate methods to identify, control for, and mitigate the effects of self-representation, the propensity to express socially responding characteristics or self-censorship in digital settings, hinders the ability of researchers to confidently interpret and generalize their findings. This article proposes applying boosted regression modelling to fill this research gap. A case study of paid Amazon Mechanical Turk workers (n = 509) is presented where workers completed psychometric surveys and provided anonymized access to their Facebook timelines. Our research finds indicators of self-representation on Facebook, facilitating suggestions for its mitigation. We validate the use of LIWC for Facebook personality studies, as well as find discrepancies with extant literature about the use of LIWC-only approaches in unobtrusive designs. Using survey data and LIWC sentiment categories as predictors, the boosted regression model classified the Five Factor personality model with an average accuracy of 74.6%. The contribution of this work is an accurate prediction of psychometric information based on short, informal text.

Original languageEnglish (US)
Article numbere0184417
JournalPloS one
Volume12
Issue number9
DOIs
StatePublished - Sep 1 2017

Fingerprint

Psychometrics
Personality
Social Media
Aptitude
Research
social networks
Research Personnel
researchers
case studies
prediction
Surveys and Questionnaires
methodology
TimeLine

ASJC Scopus subject areas

  • Biochemistry, Genetics and Molecular Biology(all)
  • Agricultural and Biological Sciences(all)

Cite this

Am I who I say I am? Unobtrusive self-representation and personality recognition on Facebook. / Hall, Margaret A; Caton, Simon.

In: PloS one, Vol. 12, No. 9, e0184417, 01.09.2017.

Research output: Contribution to journalArticle

@article{9ee756a826c54f83895b1552d1e4f3f8,
title = "Am I who I say I am? Unobtrusive self-representation and personality recognition on Facebook",
abstract = "Across social media platforms users (sub)consciously represent themselves in a way which is appropriate for their intended audience. This has unknown impacts on studies with unobtrusive designs based on digital (social) platforms, and studies of contemporary social phenomena in online settings. A lack of appropriate methods to identify, control for, and mitigate the effects of self-representation, the propensity to express socially responding characteristics or self-censorship in digital settings, hinders the ability of researchers to confidently interpret and generalize their findings. This article proposes applying boosted regression modelling to fill this research gap. A case study of paid Amazon Mechanical Turk workers (n = 509) is presented where workers completed psychometric surveys and provided anonymized access to their Facebook timelines. Our research finds indicators of self-representation on Facebook, facilitating suggestions for its mitigation. We validate the use of LIWC for Facebook personality studies, as well as find discrepancies with extant literature about the use of LIWC-only approaches in unobtrusive designs. Using survey data and LIWC sentiment categories as predictors, the boosted regression model classified the Five Factor personality model with an average accuracy of 74.6{\%}. The contribution of this work is an accurate prediction of psychometric information based on short, informal text.",
author = "Hall, {Margaret A} and Simon Caton",
year = "2017",
month = "9",
day = "1",
doi = "10.1371/journal.pone.0184417",
language = "English (US)",
volume = "12",
journal = "PLoS One",
issn = "1932-6203",
publisher = "Public Library of Science",
number = "9",

}

TY - JOUR

T1 - Am I who I say I am? Unobtrusive self-representation and personality recognition on Facebook

AU - Hall, Margaret A

AU - Caton, Simon

PY - 2017/9/1

Y1 - 2017/9/1

N2 - Across social media platforms users (sub)consciously represent themselves in a way which is appropriate for their intended audience. This has unknown impacts on studies with unobtrusive designs based on digital (social) platforms, and studies of contemporary social phenomena in online settings. A lack of appropriate methods to identify, control for, and mitigate the effects of self-representation, the propensity to express socially responding characteristics or self-censorship in digital settings, hinders the ability of researchers to confidently interpret and generalize their findings. This article proposes applying boosted regression modelling to fill this research gap. A case study of paid Amazon Mechanical Turk workers (n = 509) is presented where workers completed psychometric surveys and provided anonymized access to their Facebook timelines. Our research finds indicators of self-representation on Facebook, facilitating suggestions for its mitigation. We validate the use of LIWC for Facebook personality studies, as well as find discrepancies with extant literature about the use of LIWC-only approaches in unobtrusive designs. Using survey data and LIWC sentiment categories as predictors, the boosted regression model classified the Five Factor personality model with an average accuracy of 74.6%. The contribution of this work is an accurate prediction of psychometric information based on short, informal text.

AB - Across social media platforms users (sub)consciously represent themselves in a way which is appropriate for their intended audience. This has unknown impacts on studies with unobtrusive designs based on digital (social) platforms, and studies of contemporary social phenomena in online settings. A lack of appropriate methods to identify, control for, and mitigate the effects of self-representation, the propensity to express socially responding characteristics or self-censorship in digital settings, hinders the ability of researchers to confidently interpret and generalize their findings. This article proposes applying boosted regression modelling to fill this research gap. A case study of paid Amazon Mechanical Turk workers (n = 509) is presented where workers completed psychometric surveys and provided anonymized access to their Facebook timelines. Our research finds indicators of self-representation on Facebook, facilitating suggestions for its mitigation. We validate the use of LIWC for Facebook personality studies, as well as find discrepancies with extant literature about the use of LIWC-only approaches in unobtrusive designs. Using survey data and LIWC sentiment categories as predictors, the boosted regression model classified the Five Factor personality model with an average accuracy of 74.6%. The contribution of this work is an accurate prediction of psychometric information based on short, informal text.

UR - http://www.scopus.com/inward/record.url?scp=85029599524&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85029599524&partnerID=8YFLogxK

U2 - 10.1371/journal.pone.0184417

DO - 10.1371/journal.pone.0184417

M3 - Article

VL - 12

JO - PLoS One

JF - PLoS One

SN - 1932-6203

IS - 9

M1 - e0184417

ER -