An artificial intelligence approach for selecting effective teacher communication strategies in autism education

Effective inclusive education is key in promoting the long-term outcomes of children with autism spectrum conditions (ASC). However, no concrete consensus exists to guide teacher-student interactions in the classroom. In this work, we explore the potential of artificial intelligence as an approach in autism education to assist teachers in effective practice in developing social and educational outcomes for children with ASC. We form a protocol to systematically capture such interactions, and conduct a statistical analysis to uncover basic patterns in the collected observations, including the longer-term effect of specific teacher communication strategies on student response. In addition, we deploy machine learning techniques to predict student response given the form of communication used by teachers under specific classroom conditions and in relation to specified student attributes. Our analysis, drawn on a sample of 5460 coded interactions between teachers and seven students, sheds light on the varying effectiveness of different communication strategies and demonstrates the potential of this approach in making a contribution to autism education.

Teacher Characteristics, Knowledge and Use of Evidence-Based Practices in Autism Education in Ireland

Autism evidence-based practices (EBPs) are those with demonstrated improved outcomes for students with autism across a range of skill areas, yet issues persist in adopting these in classroom settings- particularly in general education (GE) settings. This research aimed to identify teacher training, years of experience, access to allied professionals and knowledge and use of autism EBPs in GE settings in Ireland. 369 mainstream primary school teachers reported their characteristics and their knowledge and use of EBPs. Results indicated that the majority of teachers received little initial teacher education training in autism, almost no continuous professional development (CPD) before educating a child with autism, and received little support from allied professionals. Knowledge and use of EBPs differed significantly across teacher characteristics, with findings discussed in relation to teacher training.

Exploring an e-learning community’s response to the language and terminology use in autism from two massive open online courses on autism education and technology use

Prior research has identified the divergence across different stakeholder groups in the semantic choice of language when describing autism, as members of the autism and autistic community preferred to use identity- first language (autistic person), whereas professionals were more likely to use person- first language (person with autism). This study explored 803 e-learners’ responses from their comments across two massive open online courses on autism education held between 2017 and 2019. Comments from members of the autistic and autism community and professionals were analysed together using thematic analysis, to identify shared opinions on what, why and how language should be used when describing autism across stakeholder groups. Learners agreed that autistic individuals should guide others on which terminology to use when describing autism and that the diagnostic label is a way to facilitate understanding across stakeholder groups and help the individual gain access to support. Semantic language choices may matter less as long as the person’s difficulties are clearly acknowledged, with adaptations made to meet their specific needs. Adding to a growing body of literature on terminology use in autism research and practice, we highlight that consideration for semantic choice of language use should focus on communicating an individual’s strengths and differences. Lay abstract Within the neurodiversity movement, one recent divergence is in the semantic choice of language when describing autism, as members of the autism and autistic community preferred to use identity- first language (autistic person), whereas professionals were more likely to use person-first language (person with autism). This study explored 803 e-learners’ responses from their comments across two massive open online courses on autism education held between 2017 and 2019. Learners agreed that autistic individuals should guide others on which terminology to use when describing autism, and although identity-first language acknowledges autism as part of an individual’s identity, it can also conjure up negative stereotypes and be stigmatising. Although family, friends and professionals highlighted that the diagnostic label is a way to facilitate understanding across stakeholder groups and help autistic individuals gain access to support, autistic self-advocates found the process of disclosing autism as a form of disability to conflict with their sense of identity, and broader terms such as ‘autism spectrum’ failed to capture individual strengths and weaknesses. Semantic language choices may matter less as long as the person’s difficulties are clearly acknowledged, with adaptations made to meet their specific needs. Adding to a growing body of literature on terminology use in autism research and practice, we highlight that language used when describing autism should follow the autistic individual’s lead, with the primary focus on communicating an individual’s strengths and difficulties, to foster a sense of positive autism identity and inclusivity, and enable access to appropriate support.

Teacher Characteristics, Knowledge and Use of Evidence-Based Practices in Autism Education in Ireland

This research was conducted with mainstream school teachers in the Republic of Ireland to examine their use and knowledge of EBPs for students with autism.