2025 ASEE Annual Conference & Exposition

AI-Generated Teamwork Skill Development Tool Application for Classroom and Workforce Implementation: A Social Integration Framework for Neurodiverse STEM Students

Presented at Engineering Technology Division (ETD) Technical Session 11

This Work-In-Progress paper will describe the connection between AI and High-functioning autism, a term often categorized within the broader diagnosis of Autism Spectrum Disorder (ASD), refers to individuals who have many of the same characteristics traditionally associated with autism, coupled with enhanced cognitive abilities and adaptive skills. Recently, companies have increased their recruitment of these individuals for employment opportunities, citing the need for their ability to hyperfocus with persistence, recognize patterns and pay attention to details. In academia, Professors have also notated the difficulty many of these students have with social interactions, communication, and sensory processing. Within both settings, collaborative teams are perceived to be a foundational skill set required for matriculation in industry and academia in the form of team and group work assignments. Far too often, high-functioning autistic needs are often overlooked, both in terms of representation and inclusion during the design and development process of artificial intelligence (AI) systems. This research project highlights the development of a machine learning (ML) tool designed to assist high-functioning autistics in their quest to understand and interpret social cues as it relates to teamwork skills enhancement. This AI fueled platform provides interactive training modules that simulate various collaboration scenarios, ranging from everyday interactions and to specific conversational situations often used during student teamwork assignments.

Using advanced ML algorithms, the proposed application analyzes user responses, provides real-time feedback to enhance classroom and workforce communication skills, and empowers users to engage more effectively in social interactions from a teamwork perspective. By improving their ability to communicate with neurotypical individuals, this AI-generated tool bridges communication gaps and neurodiverse pathways for autistics in search of opportunities for teamwork experiences and elevated social integration. The evaluation of the proposed solution incorporates industry experts and peer-to-peer testing results, alongside feedback from speech-language pathologists, to ensure its efficacy and usability in real-world applications.

Research Questions:
1. How do people with high-functioning autism contribute to areas like technology, pattern recognition, and problem-solving?
2. What are the potential benefits of integrating neurodiverse perspectives, particularly those of high-functioning autistic individuals, in AI development?

The proposed research tool creates role-play scenarios for neurodiverse populations, allowing them to build confidence while adapting to ideas of social norms in familiar settings, with the use of real-life scenarios. Examples of a role-play scenarios include working with a team to solve complex logic-based problems, or simply having a conversation with professors or managers. This tool features a plugin for additional soft-skill development, that will not only scan emails for social etiquette accuracy, but also offer suggestions on how to improve the conversational tone of their correspondence attempt prior to sending. Similar to Chat GPT, which includes options for helping users create dialogue for verbal and written exchanges, this machine learning-based application contains the necessary conversational tools to help users understand tone, social constructs and the proper word selection for the intended meaning they are attempting to convey. With variable settings, depending on the individual needs, the customization of this proposed tool is the first of its kind designed exclusively for neurodiverse populations seeking careers in STEM fields where soft skills are often lacking. Preliminary results have shown a positive correlation between the use of the developed tool by First-year Autistic Engineering students and the enhancement of their ability to work with team members to solve complex problems in a variety of STEM settings.

Authors
  1. Prof. L. Taylor Starr Texas A&M University [biography]
Note

The full paper will be available to logged in and registered conference attendees once the conference starts on June 22, 2025, and to all visitors after the conference ends on June 25, 2025