We characterize the public discourse in the early conversation of the #MeToo movement from Twitter data. We document and examine the content of Tweets in the first week of the #MeToo movement focusing on novel Tweets with first-person revelation of sexual assault and abuse and early life experiences of sexual abuse and assault. We use machine learning methods, Least Absolute Shrinkage and Selection Operator regressions and Support Vector Machine models, to summarize and classify the content of individual Tweets. We estimate that 11% of novel Tweets revealed details about the writer’s experience of sexual abuse or assault and 5.8% revealed early life experiences of such events. These data suggest that the mass sharing of personal experiences of sexual abuse and assault contributed to the reach of this movement, and we estimate that 6 to 34 million Tweeter users may have seen such first-person revelation.
Presented in Session 3. Population, Development, & the Environment; Data & Methods; Applied Demography