Extracting emotion data from motion data

We have been looking at how to record music related motion, and to get data streams from this. And we’ve also seen that motion and emotion are closely connected. So I’d like to ask you Alexander, do you think it’s possible to identify human emotion from motion data? I think the short answer is yes. But it’s very difficult to do. But still I think it’s important to think about that we have many different layers here. So one thing is the actual physical motion that we have and that we can measure with different types of motion capture systems. But then to understand more about what actually happens emotionally, how we would perceive this in our brain, it’s a long way.

And it’s many, many layers in between. So that’s why I think, when we work with this as researchers, we need to do this systematically and to look at the different layers separately. And for example, go from the continuous physical motion to look at how we perceive this as an action with the beginning and an end. And then from there again it’s possible to look at kind of how we experience these, some of the more expressive and emotional qualities in this. And then obviously here we also need to combine both quantitative methods and techniques, but also qualitative.

Because of course the interpretation of the data is very much connected to the cultural background, the context that this is situated in, et cetera, et cetera. So the long answer it’s difficult, and the short answer is that yes, it’s possible. Ok, so then we know that research is going on, on how to identify human emotion from motion. But what do you think, is it possible to identify emotion from motion? And in what way are the two related?