Katerina Avramides

Developing technology for autism: an interdisciplinary approach

We present an interdisciplinary methodology for designing interactive multi-modal technology for young children with autism spectrum disorders (ASDs). In line with many other researchers in the field, we believe that the key to developing technology in this context is to embrace perspectives from diverse disciplines to arrive at a methodology that delivers satisfactory outcomes for all stakeholders. The ECHOES project provided us with the opportunity to develop a technology-enhanced learning (TEL) environment that facilitates acquisition and exploration of social skills by typically developing (TD) children and children with autism spectrum disorders (ASDs). ECHOES’ methodology and the learning environment rely crucially on multi-disciplinary expertise including developmental psychology, visual arts, human–computer interaction, artificial intelligence, education, and several other cognate disciplines. In this article, we reflect on the methods needed to develop a TEL environment for young users with ASDs by identifying key features, benefits, and challenges of this approach.

Towards Systems That Care: A Conceptual Framework based on Motivation, Metacognition and Affect

This paper describes a Conceptual Framework underpinning “Systems that Care” in terms of educational systems that take account of motivation, metacognition and affect, in addition to cognition. The main focus is on motivation, as learning requires the student to put in effort and be engaged, in other words to be motivated to learn. But motivation is not the whole story as it is strongly related to metacognition and affect. Traditional intelligent educational systems, whether learner-centred or teacher-centred in their pedagogy, are characterised as having deployed their intelligence to assist in the development of the learners knowledge or skill in some domain. They have operated largely at the cognitive level and have assumed that the learner is already able to manage her own learning, is already in an appropriate affective state and also is already motivated to learn. This paper starts by outlining theories of motivation and their interactions with affect and with metacognition, as developed in the psychological and educational literatures. It then describes how such theories have been implemented in intelligent educational systems. The first part of the Conceptual Framework develops the notion of a partial hierarchy of systems in terms of their pedagogic focus. These range from traditional, cognitively intelligent systems, essentially concerned with cognition up to “Systems that Care”. Intermediate classes of system include Metacognitively Intelligent systems, Affectively Intelligent systems and Motivationally Intelligent systems. The second part of the Conceptual Framework is concerned with the design of systems. This is characterised in terms of (i) the kinds of diagnostic input data (such as the learners facial expression offering clues as to her demeanour) and (ii) the repertoire of tactical and strategic pedagogic moves (such as offering encouragement), applicable at different levels of the hierarchy. Attention is paid to metacognition, meta-affect and meta-motivation covering the capability of both the learner and the educational system to understand, reason about and regulate cognition, affect and motivation. Finally, research questions and areas of further work are identified in theory development, the role of the meta levels, and design considerations.

Societal impact of a serious game on raising public awareness: the case of FloodSim

This paper presents an evaluation of the societal impact of a simulation-based Serious Game. FloodSim was developed with the aim of raising awareness of issues surrounding flooding policy and citizen engagement in the UK. The game was played by a large number of users (N=25,701) in a period of 4 weeks. Quantitative and qualitative analyses (on a reduced data set) were carried out in order to explore the impact of FloodSim play in raising the general public awareness around flooding in the UK. The results suggest FloodSim was hugely successful in generating general public interest and there was evidence that (a) FloodSim increased awareness at a basic level and (b) that despite the simplicity of the simulation, players perceived FloodSim to be an accurate source of information about flood risk and prevention. This suggests that serious games such as FloodSim have potential to engage the public and raise awareness of societal issues. However, FloodSim only raised awareness at a basic level. It is suggested that more needs to be done to endow serious games with pedagogical principles and more care should be given to the accuracy of the information they convey. The appropriateness of games as an educational medium for raising awareness of complex, real-life issues should also be carefully considered. This study throws some light on the potential of simulation-based Serious Games to offer experiential learning, engage users with serious topics while raising public awareness and understanding of social issues such as flooding and related policymaking. Future research is outlined consisting of identifying the problems and challenges in designing and developing serious games while considering pedagogical principles.

Social communication between virtual characters and children with autism

Children with ASD have difficulty with social communication, particularly joint attention. Interaction in a virtual environment (VE) may be a means for both understanding these difficulties and addressing them. It is first necessary to discover how this population interacts with virtual characters, and whether they can follow joint attention cues in a VE. This paper describes a study in which 32 children with ASD used the ECHOES VE to assist a virtual character in selecting objects by following the characters gaze and/or pointing. Both accuracy and reaction time data suggest that children were able to successfully complete the task, and qualitative data further suggests that most children perceived the character as an intentional being with relevant, mutually directed behaviour.

Supporting children's social communication skills through interactive narratives with virtual characters

The development of social communication skills in children relies on multimodal aspects of communication such as gaze, facial expression, and gesture. We introduce a multimodal learning environment for social skills which uses computer vision to estimate the childrens gaze direction, processes gestures from a large multi-touch screen, estimates in real time the affective state of the users, and generates interactive narratives with embodied virtual characters. We also describe how the structure underlying this system is currently being extended into a general framework for the development of interactive multimodal systems.

Building autonomous social partners for autistic children

We present the design and implementation of an autonomous virtual agent that acts as a credible social partner for children with Autism Spectrum Conditions and supports them in acquiring social communication skills. The agents design is based on principles of best autism practice and input from users. Initial experimental results on the efficacy of the agent show encouraging tendencies for a number of children.

State-of-the-art in TEL to support social communication skill development in children with autism: a multi-disciplinary review

The paper reviews state-of-the-art in Technology Enhanced Learning TEL to support social communication skill development in children with autism. We identify the driving research directions, and their associated challenges, from three broad perspectives that shape TEL: pedagogical foundations, technology and learner involvement in the design process. We further explore these challenges through the discussion of ECHOES, an example state-of-the-art system. The review assists researchers working in multi-disciplinary teams to identify the new directions that are shaping state-of-the-art in order to drive successful future research projects in this area.

Using teacher inquiry to support technology-enhanced formative assessment: a review of the literature to inform a new method

ABSTRACT In this paper we review the literature on teacher inquiry (TI) to explore the possibility that this process can equip teachers to investigate students’ learning as a step towards the process of formative assessment. We draw a distinction between formative assessment and summative forms of assessment [CRELL. (2009). The transition to computer-based assessment: New approaches to skills assessment and implications for large-scale testing. In F. Scheuermann & J. Björnsson (Eds.), JRC Scientific and technical reports. Ispra: Author; Webb, M. (2010). Beginning teacher education and collaborative formative e-assessment. Assessment & Evaluation in Higher Education, 35, 597–618; EACEA. (2009). National testing of pupils in Europe: Objectives, organisation and use of results. Brussels: Eurydice; OECD. (2010b). Assessing the effects of ICT in education (F. Scheuermann & E. Pedró, Eds.). Paris: JRC, OECD]. Our review of TI is combined with a review of the research concerning the way that practices with technology can support the assessment process. We conclude with a comparison of TI and teacher design research from which we extract the characteristics for a method of TI that can be used to develop technology-enhanced formative assessment: teacher inquiry into student learning. In this review, our primary focus is upon enabling teachers to use technology effectively to inquire about their students’ learning progress.

How Mastery and Performance Goals Influence Learners’ Metacognitive Help-Seeking Behaviours When Using Ecolab II

The Ecolab software is an interactive learning environment for 10–11-year-old learners designed to help children learn about food chains and food webs. In the current chapter, we discuss the results of our recent work on achievement goal orientation and help seeking within the Ecolab environment. We situate these results within the broader landscape of our previous studies and discuss the evolutionary approach we have adopted to develop a methodology to support the design of metacognitive learning tools. This methodology has been built up over a series of empirical studies with the Ecolab software that have demonstrated that children who achieved above average learning gains use a high level of system help. In the empirical work that we focus upon in this chapter, we investigate the relationships between young learners’ metacognition: specifically their help-seeking behaviour and their achievement goal orientations. This work draws together and extends two strands of our previous research: metacognitive software scaffolding (Luckin and Hammerton. Getting to know me: Helping learners understand their own learning needs through metacognitive scaffolding. Berlin: Springer Verlag, 2002) and the influence of goal orientation on children’s learning (Harris, Yuill, & Luckin. British Journal of Educational Psychology, 78(3):355–374, 2008). Our research with Ecolab shows how tracking metacognitive behaviours—choice and use of more or less specific help—in the light of children’s goal orientations, can be used to support learning.

Exploring the interplay between human and machine annotated multimodal learning analytics in hands-on STEM activities

This poster explores how to develop a working framework for STEM education that uses both human annotated and machine data across a purpose-built learning environment. Our dual approach is to develop a robust framework for analysis and investigate how to design a learning analytics system to support hands-on engineering design tasks. Data from the first user tests are presented along with the framework for discussion.