Political Data Science

Infiltrating the #filterbubble? Slandering Donald Trump and telling racist jokes seems to be the intention of a social botnet on Twitter. There have been different stories about bot armies supporting Donald Trump. @PatrickRuffini has posted a list with bots that are likely supporting Trump. @Wired has wrote about pseudo Hispanic bots , supporting Trump . But Donald Trump is also victim of slandering bots. Morteza Shahrezaye ( @ morry_shah )  and I have found a botnet with a strange behavior: The bots are telling jokes all the time of which many are very racist, disturbing anti-Semitic and sexist. In addition, the bots post “jokes” about Donald Trump, like: “Your moma is so dump, she voted for Trump.” There are at least three possible explanations for this: There might be a racist botmaster who thinks Trump is too liberal. It could be a “fluke”: The bots are just there to tell jokes but the internet is full with racist stuff and anti-Trump jokes, so this is just what th...

My new Publication in @EPA_Journal is #openSource . Abstract The article introduces machine learning algorithms for political scientists. These approaches should not be seen as new method for old problems. Rather, it is important to understand the different logic of the machine learning approach. Here, data is analyzed without theoretical assumptions about possible causalities. Models are optimized according to their accuracy and robustness. While the computer can do this work more or less alone, it is the researcher’s duty to make sense of these models afterwards. Visualization of machine learning results therefore becomes very important and is in the focus of this paper. The methods that are presented and compared are decision trees, bagging and random forests. The later are more advanced versions of the former, relying on bootstrapping procedures. To demonstrate these methods, extreme shifts in the US budget and their connection to attention of political actors are analyzed. Th...