Bot or Not: A Twitter user classifier

Posted to Statistics  |  Tags: , ,  |  Nathan Yau

Michael W. Kearney implemented a classifier for Twitter bots. It’s called botornot:

Uses machine learning to classify Twitter accounts as bots or not bots. The default model is 93.53% accurate when classifying bots and 95.32% accurate when classifying non-bots. The fast model is 91.78% accurate when classifying bots and 92.61% accurate when classifying non-bots.

Overall, the default model is correct 93.8% of the time.

Overall, the fast model is correct 91.9% of the time.

You can enter Twitter accounts to see what the model projects here. It’s barebones, and I’m not sure what the curve represents, but it’s fun to poke at.


Interactive: When Do Americans Leave For Work?

We don’t all start our work days at the same time, despite what morning rush hour might have you think.

A Day in the Life of Americans

I wanted to see how daily patterns emerge at the individual level and how a person’s entire day plays out. So I simulated 1,000 of them.

Famous Movie Quotes as Charts

In celebration of their 100-year anniversary, the American Film Institute …

The Changing American Diet

See what we ate on an average day, for the past several decades.