Developing Age and Gender Predictive Lexica over Social Media

By Maarten Sap, Gregory J. Park, Johannes C. Eichstaedt, Margaret L. Kern, David J. Stillwell, Michal Kosinski, Lyle Ungar, H. A. Schwartz. 2014

255 citations recorded by the source corpus.

Demographic lexica have potential for widespread use in social science, economic, and business applications. We derive predictive lexica (words and weights) for age and gender using regression and classification models from word usage in Facebook, blog, and Twitter data with associated demographic labels. The lexica, made publicly available,1 achieved state-of-the-art accuracy in language based age and gender prediction over Facebook and Twitter, and were evaluated for generalization across social media genres as well as in limited message situations.

Subfields: Artificial Intelligence, Social Psychology

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 Social Psychology

Citations in the corpus

Are You a Racist or Am I Seeing Things? Annotator Influence on Hate Speech Detection on Twitter (2016, methodology): “To counteract the low coverage in Waseem and Hovy (2016), we use a lexicon trained on Twitter (Sap et al., 2014) to calculate the probability of gender.”
Finding Microaggressions in the Wild: A Case for Locating Elusive Phenomena in Social Media Posts (2019, background): “…stereotypical gender (male, female, neutral), (4) the gender stereotype lexicon of Fast et al. (2016), (5) the gender lexicon for social media from (Sap et al., 2014), (6) a manually-compiled corpus of gendered words, extended from seed list from https://www.hrc.org/resources/glossary-of-terms and…”
From ADHD to SAD: Analyzing the Language of Mental Health on Twitter through Self-Reported Diagnoses (2015, methodology): “For each user in our mental health collection we obtain age and gender estimates from the tools provided by the World Well-Being Project (Sap et al., 2014)5.”
Does ‘well-being’ translate on Twitter? (2016, methodology): “The models were then transformed into a predictive lexicon using the methods described in (Sap et al., 2014), where the weights in the lexicon were derived from the above Lasso regression model.”
Diachronic degradation of language models: Insights from social media (2018, background): “to predict users’ age and gender (Sap et al., 2014), personality (Schwartz et al.”
Returning the N to NLP: Towards Contextually Personalized Classification Models (2020, background): “…have been conducted with estimating variables such as age (Rao et al., 2010; Nguyen et al., 2011), gender (Burger et al., 2011; Bamman et al., 2014; Sap et al., 2014), ge-olocation (Eisenstein et al., 2010), political preferences (Volkova et al., 2014), socio-economic status (Preot¸iuc-Pietro et…”
Analyzing Biases in Human Perception of User Age and Gender from Text (2016, methodology): “We use Support Vector Machines (SVM) with a linear kernel and (cid:96) 1 regularization (Tibshirani, 1996), similarly to the state-of-the-art method in predicting user age and gender (Sap et al., 2014).”
Handling Bias in Toxic Speech Detection: A Survey (2022, methodology): “Waseem [108] showed that a model trained on theW&H dataset led to a performance gain by including the user’s gender as a feature [86].”
User-Level Race and Ethnicity Predictors from Twitter Text (2018, unknown): “…of previous work on predicting user traits from text (Burger et al., 2011; Rao et al., 2010; Pennacchiotti and Popescu, 2011; Schwartz et al., 2013; Sap et al., 2014; Volkova et al., 2014; Preoţiuc-Pietro et al., 2015b; Flekova et al., 2016b; Preoţiuc-Pietro et al., 2016; Preoţiuc-Pietro et…”
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).”
The role of personality, age, and gender in tweeting about mental illness (2015, methodology): “…have used on usergenerated text and complementary features in order to predict different user traits such as: age (Nguyen et al., 2011), gender (Sap et al., 2014), location (Cheng et al., 2010), impact (Lampos et al., 2014), political preference (Volkova et al., 2014), temporal orientation…”
User Classification with Multiple Textual Perspectives (2016, background): “User attribute classification, also namely user classification for short, is a task which aims to leverage user-generated content to automatically predict user’s attributes, such as gender (Wang et al., 2015), age (Rao et al., 2010; Sap et al., 2014) and location (Cheng et al., 2010).”
Studying User Income through Language, Behaviour and Affect in Social Media (2015, methodology): “Age and gender are predicted using text-based models described in [32].”
Computational Sociolinguistics: A Survey (2016, methodology): “Vyas et al. (2014) studied the impact of different preprocessing steps on POS tagging of English-Hindi data collected from Facebook.”