Blog
-
Processing
I’ve been playing with Processing recently. It’s a really cool tool for graphical programming developed at the intersection between art and technology. It’s been around for quite a while and the developers have done a great job of making it accessible and easy to pick up. The documentation is first class and I’ve been really enjoying Adam Shiffman’s The Nature of Code book which demonstrates how to use Processing to model various phenomena including motion and artificial life.
-
Network analysis updated - Communities within Denmark's Elite
After feedback from Anton Grau Larsen I’ve done two more versions of the graph an attempt to make the communities within the network more apparent. To do this I have transformed the graphs so that instead of showing individuals and organisations, I now show either individuals or organisations. In the first case individuals are directly connected through shared membership of organisations while in the second case organisations are directly connected through shared members. The nodes have also been sized using betweenness centrality meaning that those nodes which are key connectors to other nodes will be relatively bigger; these are the nodes that bind the graph together.
-
Network Analysis - Denmark's Elite
I’ve been messing around recently with network visualisations using Gephi and I wanted to look at an interesting dataset. To that end I pulled down some of the data from Magtelite.dk which is based on a PhD done by Christopher Ellersgaard and Anton Grau Larsen.
-
More similarity - beyond Bag O'Words
In my previous posts I looked at some ways of measuring document similarity and applied these to a concrete example. Now, as I mentioned, Bag O’ Words is cool and everything, but it’s a bit naive.
-
Experiment 1
Based on the techniques described in my previous post, I decided to see if they could be applied to a recent controversy in Danish politics.
-
Getting started with similarity
One of the most fundamental concepts that I’m researching is textual similarity: what is it that makes two texts similar or dissimilar? This is a well studied problem in Natural Language Processing and I will present here some of my findings from my initial research of the field. This is only intended to be a summary for my own sake, so if you’re here looking for in-depth analysis, you are in the wrong place.
-
Hello World
Welcome to my blog. I’ve started this site to log my exploration of the field of Text Mining as it can be applied to Social Sciences. I’m glad you’re here, but please bear in mind that it’s not meant for professional consumption at this stage. I’m still very much an amateur within the field and the level here will reflect this. For more information, see the about page.
subscribe via RSS