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

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.

Self-reported frequency of swearing in English: do situational, psychological and sociobiographical variables have similar effects on first and foreign language users?

“…It confirms Vingerhoets et al's (2013) conclusion of their overview of the psychological and neurological literature on swearing, namely that having an antisocial personality is linked to increased swearing (301). The effect of Psychoticism is also indirectly confirmed by the findings of Mehl et al (2006) and Schwartz et al (2013) whose participants scoring low on Agreeableness and Conscientiousness used more swearwords. The weaker effect of Psychoticism among LX users could be linked to their awareness that their pragmatic calibration might not have been precise enough to meet out the appropriate type and amount of swearwords which could have prompted violence in interactions with strangers.…”

“…Extraversion could have a weaker effect for the L1 users as this identity issue does not apply to them. More neurotic, anxious individuals are more responsive to threat or stress which could translate in increased use of swearing, as Schwartz et al (2013) reported for Facebook updates. Interestingly, the effect was strongest for L1 users swearing with their friends and for LX users swearing when alone.…”

“…A single significant negative correlation emerged between Openness to Experience among the male participants and the amount of swearwords (871). Schwartz et al (2013) adopted a different approach, using an open-vocabulary technique, collecting 700 million words and phrases from 19 million Facebook status updates written by 136,000 people. About 75,000 participants took a personality questionnaire (the International Personality Item Pool), and striking relations were found between personality, gender, age and language.…”

Exploring Small, Confirming Big: An alternative system to The New Statistics for advancing cumulative and replicable psychological research

“…Sentiment analysis of social media data is becoming increasingly common (e.g., Schwartz et al, 2013), and could range from utilizing relatively simple pre-programmed psychological language dictionaries (e.g., Pennebaker, Chung, Ireland, Gonzales, & Booth, 2007), to complex machine learning/data-driven language categories (Eichstaedt et al, 2015).…”

Big Data-Driven Marketing: How Machine Learning Outperforms Marketers’ Gut-Feeling

“…A data-driven approach might lead to an increased efficiency of text-based campaigns by being one step closer to delivering "the right offer to the right customer". For example, previous research showed that data-driven approaches can reliably predict mobile phone and Facebook user's personality [3][4][5]18], sexual orientation [6], or romantic relationships [7].…”