Inferring Gender from the Content of Tweets: A Region Specific Example

By Clayton Fink, Jonathon Kopecky, M. Morawski. 2012

66 citations recorded by the source corpus.

There is growing interest in using social networking sites such as Twitter to gather real-time data on the reactions and opinions of a region's population, including locations in the developing world where social media has played an important role in recent events, such as the 2011 Arab Spring. However, many interesting and important opinions and reactions may differ significantly within a given region depending on the demographics of the subpopulation, including such categories as gender and ethnicity. Unfortunately, the demographic characteristics of social media users are often unknown because such categories are not always captured in user metadata. Twitter, for example, does not capture a user’s gender in their profile, and inferring gender from first names is difficult since Twitter users are not required to give their real names. There is thus a need for automated methods that can infer such hidden attributes of users from other data sources. In this paper we describe a method to infer the gender of Twitter users from only the content of their tweets. Looking at Twitter users from the West African nation of Nigeria, we applied supervised machine learning using features derived from the content of user tweets to train a classifier. Using unigram features alone, we obtained an accuracy of 80% for predicting gender, suggesting that content alone can be a good predictor of gender. An analysis of the highest weighted features shows some interesting distinctions between men and women both topically and emotionally. We argue that approaches such as the one described here can give us a clearer picture of who is utilizing social media when certain user attributes are unreliable or not available.

Subfields: Artificial Intelligence, Information Systems

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 Information Systems

Citations in the corpus

"How Old Do You Think I Am?" A Study of Language and Age in Twitter (2013, methodology): “Some approaches used lists of male and female names, for example obtained using Facebook (Fink, Kopecky, and Morawski 2012) or from the US social security department (Zamal, Liu, and Ruths 2012; Bamman, Eisenstein, and Schnoebelen 2012).”
Why Gender and Age Prediction from Tweets is Hard: Lessons from a Crowdsourcing Experiment (2014, methodology): “A variety of datasets have been used, including Twitter (Rao et al., 2010; Bamman et al., 2014; Fink et al., 2012; Bergsma and Van Durme, 2013; Burger et al., 2011), blogs (Mukherjee and Liu, 2010; Schler et al.”
From ADHD to SAD: Analyzing the Language of Mental Health on Twitter through Self-Reported Diagnoses (2015, background): “Since Twitter does not provide demographic information for users, these insights have been broadly applied to inferring demographic information from social media (Volkova et al., 2015; Fink et al., 2012; Burger et al., 2011; Rao et al., 2011; Rao et al., 2010).”
Computational Sociolinguistics: A Survey (2016, methodology): “However, models based on LIWC alone tend to perform worse than unigram/ngram models (Fink, Kopecky, and Morawski 2012; Nowson and Oberlander 2006).”
Write Like I Write: Herding in the Language of Online Reviews (2014, methodology): “For instance, language behaviors in Twitter have been used to infer user characteristics including gender (Fink, Kopecky, and Morawski 2012), age (Nguyen et al. 2013) and even ethnicity (Pennacchiotti and Popescu 2011).”