The word autonomy is often used in the discussion of software-based music-generating systems. Whilst the term conveys a very clear concept — the sense of self-determination of a system — attempts to formalise autonomy are at an early stage, and the term is subject to a range of interpretations when practically applied. We consider how the evaluation of music-generating systems will be enhanced by a clearer understanding of autonomy and its application to music. We discuss existing definitions and approaches to quantifying autonomy and consider, through a series of examples, the information that is required in order to make precise formal judgements about autonomy, and the identification of relevant levels at which the principle of autonomy applies in music. We conclude that automated measures can supplement human evaluation of autonomy, but that (a) automated measures must be supported by sound reasoning about the features and timescales used in the measurement, and (b) they are improved by a having knowledge of the internal working of the system, rather than taking a black box approach. We consider multi-dimensional representations of system behaviour that may capture a richer sense of the notion of autonomy. Finally, we propose an approach to automatically probing music systems as a means of determining an autonomy `portrait'.

The automatic orchestration problem is that of assigning instruments or sounds to the notes of an unorchestrated score. This is related to, but distinct from, problems of automatic expressive interpretation. A simple algorithm is described that successfully orchestrates scores based on analysis of one musical structure -- the "Z-chain."

In this paper, we survey techniques used in intelligent tutoring systems (ITSs) to model student knowledge. The three techniques that we review in detail are knowledge tracing, performance factor analysis, and matrix factorization. We also briefly cover other techniques that have been used. This review is meant to be a repository of knowledge for those who want to integrate these techniques into serious games. It is also meant to increase awareness and interest as to the techniques available that can be integrated into serious games.

The net result of this Because these approaches are not grounded in the core approach should be to either provide a viable alternative to processes that drive human action, the resultant outputs - classical artificial intelligence / machine learning (AI, ML) predictions of behavior, estimates of errors and the like - approaches or. Alternatively, to provide a more do not provide a robust basis for representing human users neurocognitively - inspired approach to developing these to the systems with which they are interacting.

Artificial Intelligence (AI) and Personalization are both essential - How do we relate content (the factual knowledge aspects of all games, be they serious or entertainment contained, game mechanics) and context (experiences based. In this research the role of AI and Personalization is and activities) to pedagogical goals towards supporting however focused upon the context of Serious Games (SG) in pedagogically-driven design and development of SGs? particular. A concerted research direction is necessary in this From these two high-level questions we derived a more area so as to establish future benchmarks and metrics for the pragmatic approach to AI and Personalization based on: In effective use of AI and Personalization in serious games design what ways can personalization improve learning and adapt and will benefit relevant research communities in providing best to learner requirements?

In this paper, methods and models for the design of educational interventions and usable systems are presented and synthesized. The purpose is to suplliment the design process with educational considerations and discern design principles for the development of serious STEM games. This synthesis can contribute to the design of the next generation of technologically enhanced learning environments.

Manual image annotation is a tedious and time-consuming task, while automated methods are error prone and limited in their results. Human computation, and especially games with a purpose, have shown potential to create high quality annotations by "hiding the complexity" of the actual annotation task and employing the "wisdom of the crowds". In this demo paper we present two games with a single purpose: finding regions in images that correspond to given terms. We discuss approach, implementation, and preliminary results of our work and give an outlook to immediate future work.

This paper describes a prototype of a two-player collaborative 2D puzzle game, designed to elicit task-oriented situated dialog. In this game players use a text-based chat to coordinate their actions in pushing a ball through a maze of obstacles. The game will be used to collect corpora of human-human interactions in this environment. The data will be used to study how language with actions are interleaved and influence each other in situated dialog. The ultimate goal is to build a computational model of these behaviors.

This paper presents a tool geared towards the collaboration of a human and an artificial designer for the creation of game content. The framework combines procedural content generation using stochastic search with user input in the form of an initial goal statement as well as preference of generated results. Feedback from industry experts in a pilot user experiment showcased the limitations of this approach and the protocol chosen for evaluating the authoring tool. The limitations are discussed with respect to the suitability of interactive evolution for creative design and the design of experimental protocols for evaluating authoring tools for games.

Location-based games are an emerging paradigm for training, simulation, entertainment, health and many other domains. In this paper, we consider the role of location-based games as a platform for data collection and analysis of human behavior. We also examine how human teams perform in a disaster scenario when such a scenario is mapped to a game environment conducted as a location-based augmented reality game. We use a pilot experiment to study human behavior between simulated disaster rescue teams and an integrated commander for the purpose of future research into improving exploitation of local tasks versus exploration of assigned objectives by disaster response teams. We show the results of our pilot experiment, analyze the effectiveness of this game as a data collection platform and then investigate how additional experiments may be conducted to formalize this problem further.