Sorry, just noticed this. All of my publications are available on my site: http://www.gamesbyangelina.org/publications/ Paywalls are shit.

Haha. It'll only resort to randomness if it can't find a justification for something else. To give you an idea, let's take the music example. ANGELINA has the term 'founder'. It uses a database of words and emotions a colleague of mine built up, called Metaphor Magnet, to find emotions people express towards this concept. One of the top ones of 'charmed' - as in, people feel charmed by founders. This is probably because of the relationship with cults and sects, as seen in the title. Once it has that emotion, it tries to narrow it down towards an emotion it can use to search a music database. To do this, it runs 'charmed' against each of the 20 emotions in the music database, and uses DISCO - a word similarity tool - to see which is nearest. It chooses a piece of music based on this emotion as a result. The fact that it looks like randomness to you is a problem with perception that software have, I think. It's a common discussion point at the Computational Creativity Conference. Anyway, thanks for commenting! :)

I'm Mike, the chap behind this research. I'm glad to see a healthy dose of skepticism in the comments here! I just wanted to clear up a few points: first, I'm not claiming to have designed anything world-changing, this is just another step in the very early days of a very, very long road. Over the next few years I hope to get ANGELINA inventing game mechanics, designing graphical styles, commentating on its own developments, and producing a wider variety of games than ever before. But I hope you'll all still be asking questions and being critical, nevertheless. If you'd like to follow the project and let me know what you think of how things turn out, I blog at gamesbyangelina.org and I tweet @mtrc. Thanks for sharing the work!

I sure hope not, I'm writing a thesis on it next month! ;) This version of ANGELINA is a new step in the research, as I've just started a new grant to tide me over for the end of my PhD. The main aims were: 1. Implementing the system in Unity (to be more flexible and use the editor's extensibility) 2. Building a more general system so I won't have to reimplement it every 12 months as I did during my PhD 3. Making ANGELINA less dependent on specific input types and able to take generic phrases or themes, so it could enter game jams The grant has just begun, but my PhD is just ending - so this is both the newest stuff ANGELINA has done, while simultaneously only being foundational for what I hope to do over the next 2 years. This year I hope to bring over work I've done in 2D on inventing game mechanics via code generation, and build it into Unity. But unfortunately that wasn't quite there yet. Nevertheless, entering ANGELINA into a game jam now will hopefully help me show progress as each future game jam passes. Over time it'll smell less like bullshit, and more like an exciting new bit of research. :)