Using Twitter to map racist and hate speech

twitterby eldh

 Mapping Racist Tweets in Response to President Obama’s Re-election
[Via floatingsheep:]

During the day after the 2012 presidential election we took note of a spike in hate speech on Twitter referring to President Obama’s re-election, as chronicled by Jezebel (thanks to Chris Van Dyke for bringing this our attention). It is a useful reminder that technology reflects the society in which it is based, both the good and the bad.  Information space is not divorced from everyday life and racism extends into the geoweb and helps shapes its contours; and in turn, data from the geoweb can be used to reflect the geographies of racist practice back onto the places from which they emerged.

Using DOLLY we collected all the geocoded tweets from the last week (beginning November 1) with racist terms that also reference the election in order to understand how these everyday acts of explicit racism are spatially distributed. Given the nature of these search terms, we’ve buried the details at the bottom of this post in a footnote [1].


Social media allows us to collect data that is almost impossible to get otherwise. And it is relatively easy to get answers to questions.

Here they were able to examine the locations in the US where racist tweets dealing with the election originated. They then normalized the results against the entire number of tweets from that state to see whether they had more racist tweets than expected for the amount of Twitter traffic coming from them.

That resulted in this map:


Yellow are states that had fewer racist tweets mentioning the election than expected and shades of green show states with more than expected numbers of hateful tweets.

Here is a map of the Electoral College votes for each state:

voting map

First we can see that most of the states that  had fewer hateful tweets than expected went for Obama. Not too unexpected.

The South had the highest concentration of racist tweets. Again. Not too unexpected that people would take out anger at losing in inappropriate ways.

There are some unexpected things. Not many people would have predicted that Minnesota or Utah would have such large numbers of racist tweets regarding the election. Utah took the results very hard – the only states with more racist tweets are Georgia, Alabama and MIssissippi.

Washington State is exactly average, being the only state to have exactly the number of racist tweets expected.

And it is unexpected that Oklahoma and Arizona – two strong red states – would have so few racist tweets. They have at least half as many as Washington State. Oklahoma has the same relative amount as California. Arizona has relatively fewer than New York.

In fact Arizona has the fewest of ANY state except one – Rhode Island. They have a lot of tweets but NO racist ones that fit the criteria.

So some interesting things learned from a simple dive into social media data. Arizona and Oklahoma dealt with the election results much better than expected while Minnesota was much worse.

And Rhode Island seems like it’s the least hateful state in the country.