TouchStory: Interactive Software Designed to Assist Children with Autism to Understand Narrative
The work described in this thesis falls under the umbrella of the Aurora project (Aurora 2000). Aurora is a long-term research project which, through diverse studies, investigates the potential enhancement of the everyday lives of children with autism through the use of robots, and other interactive systems, in playful contexts. Autism is a lifelong pervasive disability which affects social interaction and communication. Importantly for this thesis, children with autism exhibit a deficit in narrative comprehension which adversely impacts their social world. The research agenda addressed by this thesis was to develop an interactive software system which promotes an understanding of narrative structure (and thus the social world) while addressing the needs of individual children. The conceptual approach developed was to break down narrative into proto-narrative components and address these components individually through the introduction of simple game-like tasks, called t-stories, presented in a human-computer interaction context. The overarching hypothesis addressed was that it is possible to help children with autism to improve their narrative skills by addressing proto-narrative components independently. An interactive software system called TouchStory was developed to present t-stories to children with autism. Following knowledge of the characteristics and preferences of this group of learners TouchStory maintained strong analogies with the concrete, physical world. The design approach was to keep things simple, introducing features only if necessary to provide a focussed and enjoyable game. TouchStory uses a touch-sensitive screen as the interaction device as it affords immediate direct manipulation of the t-story components. Socially mediated methods of requirements elicitation and software evaluation (such as focus groups, thinking aloud protocols, or intergenerational design teams) are not appropriate for use with children with autism who are not socially oriented and, in the case of children with ‗lower functioning‘ autism, may have very few words or no productive language. Therefore a new strategy was developed to achieve an inclusive, child-centred design; this was to interleave prototype development with evaluation over several long-term trials. The trials were carried out in the participants‘ own school environments to provide an ecologically valid contextual enquiry. In the first trial 18 participants were each seen individually once. The second and third trials were extended studies of 12 and 20 school visits with 12 and 6 participants respectively; each participant was seen individually on each school visit, provided that the participant was at school on the day of the visit. Evaluation was carried out on the basis of video recordings of the sessions and software logs of the on-screen interactions. Individual learning needs were addressed by adapting the set of t-stories presented to the participant on the basis of success during recent sessions. No ordering of difficulty among the proto-narrative categories could be known a priori for any individual child, and may vary from child to child. Therefore the intention was to gradually, over multiple sessions, increase the proportion of t-stories from proto-narrative categories which the individual participant found challenging, while retaining sufficient scope for the expression of skills already mastered for the session to be enjoyable and rewarding. The adaptation of the software was achieved by introducing a simple adaptive formula, evaluating it over successive long terms trials, and increasing the complexity of the formula only where necessary. Results indicate that individual participants found the interactive presentation of the simple game-like tasks engaging, even after repeated exposures on as many as 20 occasions. The adaptive formula developed in this study did, for engaged participants, focus on the proto-narrative categories which the participant needed to practice but was likely to succeed; that is it did target an effective learning zone. While little evidence was seen of learning with respect to the fully developed narratives encountered in everyday life, results strongly suggest that some participants were actively engaged in self-directed, curiosity-driven activity that functioned as learning in that they were able to transfer knowledge about the appropriateness of particular responses to previously unseen t-stories. This thesis was driven by the needs of children with autism; contributions are made in a number of cognate areas. A conceptual contribution was made by the introduction of the proto-narrative concept which was shown to identify narrative deficits in children with autism and to form a basis for learning. A contribution was made to computational adaptation by the development of a novel adaptive formula which was shown to present a challenging experience while maintaining sufficient predictability and opportunities for the expression of skills already mastered to provide a comfortable experience for children with autism. A contribution was made to software development by showing that children with autism may be included in the design process through iterative development combined with long term trials. A contribution was made to assistive technology by demonstrating that simplicity together with evaluation over long term trials engages children with autism and is a route to inclusion. We cannot expect any magic fixes for children with autism, progress will be made by small steps; this thesis forms a small but significant contribution.