Personality, Gender, and Age in the Language of Social Media: The Open-Vocabulary Approach

By H. A. Schwartz, Johannes C. Eichstaedt, Margaret L. Kern, Lukasz Dziurzynski, Stephanie Ramones, Megha Agrawal, Achal Shah, Michal Kosinski, David J. Stillwell, Martin E. P. Seligman and 1 more. 2013

1,750 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence, Clinical Psychology, Human-Computer Interaction

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Clinical Psychology

In Human-Computer Interaction

Citations in the corpus

Survey of the State of the Art in Natural Language Generation: Core tasks, applications and evaluation (2017, background): “…phenomenon, the linguistic features of personality are only indirectly reflected in speaking or writing (a hypothesis underlying much work on detection of personality and other features in text, including Oberlander & Nowson, 2006; Argamon et al., 2007; Schwartz et al., 2013; Youyou et al., 2015).”
It's a Man's Wikipedia? Assessing Gender Inequality in an Online Encyclopedia (2015, background): “Gender inequalities in Social Media: In (Szell and Thurner 2013) the author study a communication network in a MMOG and find a similar effect as (Smoreda and Licoppe 2000).”
Women through the glass ceiling: gender asymmetries in Wikipedia (2016, background): “[30] H Andrew Schwartz, Johannes C Eichstaedt, Margaret L Kern, Lukasz Dziurzynski, Stephanie M Ramones, Megha Agrawal, Achal Shah, Michal Kosinski, David Stillwell, Martin EP Seligman, et al.”
Connotation Frames of Power and Agency in Modern Films (2017, background): “Women tend to use I and you pronouns more, whereas men use we and they pronouns more, echoing real life (Schwartz et al., 2013).”
Automatic personality assessment through social media language. (2015, methodology): “For example, Schwartz et al. (2013a) illustrated how the language from Twitter can be used to predict the average life satisfaction of U.S. counties.”
Understanding User Profiles on Social Media for Fake News Detection (2018, methodology): “We choose these three features because they are not directly provided with user meta data but they are commonly used to better describe users [17].”
New Talent Signals: Shiny New Objects or a Brave New World? (2016, background): “For example, the words that neurotics use in blogs include “awful,” “horrible,” and “depressing,” whereas extraverts talk about “bars,” “drinks,” and “Miami” (Schwartz et al., 2013; Yarkoni, 2010).”
Cybercrime detection in online communications: The experimental case of cyberbullying detection in the Twitter network (2016, methodology): “The aforementioned study (Schwartz et al., 2013) has developed an open vocabulary by analyzing 700 million words, phrases, and topic instances collected from social media and determined the words related to age, gender, and personality.”
Beyond Binary Labels: Political Ideology Prediction of Twitter Users (2017, background): “Applications include prediction of age (Rao et al., 2010; Flekova et al., 2016b), gender (Burger et al., 2011; Sap et al., 2014), personality (Schwartz et al., 2013; Preoţiuc-Pietro et al., 2016), socioeconomic status (Preoţiuc-Pietro et al., 2015a,b; Liu et al., 2016c), popularity (Lampos et…”
Extracting Human Temporal Orientation from Facebook Language (2015, background): “…proportion of works have focused on demographics (Argamon et al., 2009; Goswami et al., 2009; Burger et al., 2011; Al Zamal et al., 2012; Bergsma et al., 2013; Sap et al., 2014). and personality prediction (Mairesse et al., 2007; Iacobelli et al., 2011; Schwartz et al., 2013; Park et al., 2015).”
Returning the N to NLP: Towards Contextually Personalized Classification Models (2020, background): “, 2014), and a range of psychological traits and issues (Schwartz et al., 2013; Park et al., 2015; Sumner et al., 2012; Guntuku et al., 2017; Coppersmith et al., 2014).”
Emphasizing personal information for Author Profiling: New approaches for term selection and weighting (2018, methodology): “In the case of social media documents, AP faces extra challenges derived from the informal communication [2,3] ; for example, texts tend to contain grammatical errors, ab-breviations, slang words, and even sometimes texts are spurious or automatically generated by bots.”
Social Networking Sites, Depression, and Anxiety: A Systematic Review (2016, background): “This is an important consideration for future research as the social connection that may be gained through SNSs may provide more benefit for older users as quality of the interactions, particularly through language use, may vary significantly over the life span [142].”