Search
Program Calendar
Browse By Day
Browse By Time
Browse By Person
Browse By Session Type
Personal Schedule
Sign In
Deadlines
Policies
Updating Your Submission
Accessible Presentation
FAQs
X (Twitter)
Search Tips
About Annual Meeting
The rise of big data has generated new opportunities for social inquiry. Yet, sociologists have been slow to use big data in research. One reason is because there remains ambiguity around whether big data provides valid and representative measures of social phenomenon. In this study, I test whether one form of big data, tweets about feminism, provide a valid measure of public opinion about gender. Through qualitative and naïve Bayes sentiment analysis of nearly 120,000 tweets, I calculate region, state, and county level twitter sentiment toward feminism and test how strongly these measures correlate with aggregated gender attitudes from the General Social Survey. Then, I examine whether twitter sentiment represents the gender attitudes of diverse populations by using multilevel models to predict the effect of twitter sentiment on individuals’ gender attitudes across race, class, and gender. Results indicate that twitter sentiment toward feminism is highly correlated with surveyed gender attitudes, suggesting that twitter is a valid measure of public opinion about gender. However, twitter sentiment is not fully representative. The gender attitudes of non-whites and the less educated are unrelated to twitter sentiment, indicating limits in the extent to which generalizable inferences can be drawn from twitter data.