The Facebook Diversity Study and Its Discontents

How diverse is the social media world? While some consider the relative anonymity of the online setting to be a great equalizer, we here at YouJustGetMe have published significant research indicating that people are people whether online or off. The Facebook Data Team was intrigued by the question of the ethnic diversity of their network, and has published a study asking "How Diverse Is Facebook?"

The study extrapolated race by looking at last names of Facebook users online at a given moment and comparing it to data from the US Census Bureau and the National Telecommunications and Information Administration. 

The Facebook Data team posits that by using the statistical technique known as mixture-modeling -  put in extremely simple terms, a mathematical model for estimating the density of a population through a statistical equation - that their study is able to accurately gauge the ethnic backgrounds of its users. "We imagine that people come from a population with unknown racial/ethnic proportions," explains the Data Team. "Individuals then get assigned names based on their race/ethnicity. Under this assumption, determining the ethnic makeup of Facebook becomes a problem of back-solving each individual's ethnicity using only their revealed name. By allowing the Facebook population to be different from the Census population, and for each name to inform our interpretation of every other name, this technique allows us to more accurately estimate the expected number of Facebook users of a given race or ethnicity at any given time."

Many of the criticisms that have been raised in the post's comments are worth taking note for researchers and casual users alike. The study has been criticized for being wholly United States-centric - and while Americans are strongly represented in Facebook users, they may be unusually diverse in comparison with other cultures. 

Another criticism leveled against the study hinges on their choice of ethnic identifiers. Notably absent from the categories is an option for Middle Eastern or Arabian - a sizable minority in the US and an important racial classification worldwide. This is due to the US Census Bureau's race and ethnic classifications, which groups people of Middle Eastern descent in the "White" category. 

What do you think? It's exciting to see other folks engaged in research in the same vein as YouJustGetMe, but what caveats should be applied to that research? Sound off in the comments!