How is player experience best labelled and, in turn, captured by a computational model? Which machine learning methods seem to be more appropriate for the task? What are the challenges of processing player demonstrations? In this talk, I will attempt to address the above questions primarily by viewing the field of player experience modelling from an ordinal perspective. I will showcase a number of representative studies demonstrating the benefits of such a perspective and reflect on the lessons learned from our projects at the Institute of Digital Games in Malta.