Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2013 Sep 25;8(9):e73791.
doi: 10.1371/journal.pone.0073791. eCollection 2013.

Personality, gender, and age in the language of social media: the open-vocabulary approach

H Andrew Schwartz  1 , Johannes C Eichstaedt, Margaret L Kern, Lukasz Dziurzynski, Stephanie M Ramones, Megha Agrawal, Achal Shah, Michal Kosinski, David Stillwell, Martin E P Seligman, Lyle H Ungar
Affiliations

Personality, gender, and age in the language of social media: the open-vocabulary approach

H Andrew Schwartz et al. PLoS One. .

Abstract

We analyzed 700 million words, phrases, and topic instances collected from the Facebook messages of 75,000 volunteers, who also took standard personality tests, and found striking variations in language with personality, gender, and age. In our open-vocabulary technique, the data itself drives a comprehensive exploration of language that distinguishes people, finding connections that are not captured with traditional closed-vocabulary word-category analyses. Our analyses shed new light on psychosocial processes yielding results that are face valid (e.g., subjects living in high elevations talk about the mountains), tie in with other research (e.g., neurotic people disproportionately use the phrase 'sick of' and the word 'depressed'), suggest new hypotheses (e.g., an active life implies emotional stability), and give detailed insights (males use the possessive 'my' when mentioning their 'wife' or 'girlfriend' more often than females use 'my' with 'husband' or 'boyfriend'). To date, this represents the largest study, by an order of magnitude, of language and personality.

PubMed Disclaimer

Conflict of interest statement

Competing Interests: The authors have declared that no competing interests exist.

Figures

Figure 1
Figure 1. The infrastructure of our differential language analysis.
1) Feature Extraction. Language use features include: (a) words and phrases: a sequence of 1 to 3 words found using an emoticon-aware tokenizer and a collocation filter (24,530 features) (b) topics: automatically derived groups of words for a single topic found using the Latent Dirichlet Allocation technique , (500 features). 2) Correlational Analysis. We find the correlation ([Image: see text] of ordinary least square linear regression) between each language feature and each demographic or psychometric outcome. All relationships presented in this work are at least significant at a Bonferroni-corrected [Image: see text] . 3) Visualization. Graphical representation of correlational analysis output.
Figure 2
Figure 2. Correlation values of LIWC categories with gender, age, and the five factor model of personality.
[Image: see text]: Effect size as Cohen's [Image: see text] values from Newman et al. 's recent study of gender (positive is female, [Image: see text] not significant at [Image: see text]) . [Image: see text]: Standardized linear regression coefficients adjusted for sex, writing/talking, and experimental condition from Pennebaker and Stone's study of age ([Image: see text] not significant at [Image: see text]) . [Image: see text]: Spearman correlations values from Yarkoni's recent study of personality ([Image: see text] not significant at [Image: see text]). our [Image: see text]: Standardized multivariate regression coefficients adjusted for gender and age for this current study over Facebook ([Image: see text] =  not significant at Bonferroni-corrected [Image: see text]).
Figure 3
Figure 3. Words, phrases, and topics most highly distinguishing females and males.
Female language features are shown on top while males below. Size of the word indicates the strength of the correlation; color indicates relative frequency of usage. Underscores (_) connect words of multiword phrases. Words and phrases are in the center; topics, represented as the 15 most prevalent words, surround. ([Image: see text]: [Image: see text] females and [Image: see text] males; correlations adjusted for age; Bonferroni-corrected [Image: see text]).
Figure 4
Figure 4. Words, phrases, and topics most distinguishing subjects aged 13 to 18, 19 to 22, 23 to 29, and 30 to 65.
Ordered from top to bottom: 13 to 18 19 to 22 23 to 29, and 30 to 65. Words and phrases are in the center; topics, represented as the 15 most prevalent words, surround. ([Image: see text]; correlations adjusted for gender; Bonferroni-corrected [Image: see text]).
Figure 5
Figure 5. Standardized frequency of topics and words across age.
A. Standardized frequency for the best topic for each of the 4 age groups. Grey vertical lines divide groups: 13 to 18 (black: [Image: see text] out of [Image: see text]), 19 to 22 (green: [Image: see text]), 23 to 29 (blue: [Image: see text]), and 30+ (red: [Image: see text]). Lines are fit from first-order LOESS regression controlled for gender. B. Standardized frequency of social topic use across age. C. Standardized ‘I’, ‘we’ frequencies across age.
Figure 6
Figure 6. Words, phrases, and topics most distinguishing extraversion from introversion and neuroticism from emotional stability.
A. Language of extraversion (left, e.g., ‘party’) and introversion (right, e.g., ‘computer’); [Image: see text]. B. Language distinguishing neuroticism (left, e.g. ‘hate’) from emotional stability (right, e.g., ‘blessed’); [Image: see text] (adjusted for age and gender, Bonferroni-corrected [Image: see text]). Figure S8 contains results for openness, conscientiousness, and agreeableness.
See this image and copyright information in PMC

References

    1. Lazer D, Pentland A, Adamic L, Aral S, Barabasi AL, et al. (2009) Computational social science. Science 323: 721–723. - PMC - PubMed
    1. Weinberger S (2011) Web of war: Can computational social science help to prevent or win wars? the pentagon is betting millions of dollars on the hope that it will. Nature 471: 566–568. - PubMed
    1. Miller G (2011) Social scientists wade into the tweet stream. Science 333: 1814–1815. - PubMed
    1. Facebook (2012) Facebook company info: Fact sheet website. Available: http://newsroom⋅fb⋅com. Accessed 2012 Dec.
    1. Golder S, Macy M (2011) Diurnal and seasonal mood vary with work, sleep, and daylength across diverse cultures. Science 333: 1878–1881. - PubMed

Publication types