Abstract Most software applications contain graphics such as charts, diagrams and maps. Currently, these graphics are designed with a “one size fits all" approach and do not cater to the needs of people with disabilities. Therefore, when using software with graphics, a colour-impaired user may struggle to interpret graphics with certain colours, and a person with dyslexia may struggle to read the text labels in the graphic. Our research addresses this issue by developing a framework that generates adaptive and accessible information graphics for multiple disabilities. Uniquely, the approach also serves people with multiple simultaneous disabilities. To achieve these, we used a case study of public space floorplans presented via a web tool and worked with four disability groups: people with low vision, colour blindness, dyslexia and mobility impairment. Our research involved gathering requirements from 3 accessibility experts and 80 participants with disabilities, developing a system to generate adaptive graphics that address the identified requirements, and conducting an evaluation with a total of 99 participants with disabilities. The evaluation showed that users found our solution easy to use and suitable for most of their requirements. The study also provides recommendations for front-end developers on engineering accessible graphics for their software and discusses the implications of our work on society from the perspective of public space owners and end users.

Developing user-centred applications that address diverse user needs requires rigorous user research. This is time, effort and cost-consuming. With the recent rise of generative AI techniques based on Large Language Models (LLMs), there is a possibility that these powerful tools can be used to develop adaptive interfaces. This paper presents a novel approach to develop user personas and adaptive interface candidates for a specific domain using ChatGPT. We develop user personas and adaptive interfaces using both ChatGPT and a traditional manual process and compare these outcomes. To obtain data for the personas we collected data from 37 survey participants and 4 interviews in collaboration with a not-for-profit organisation. The comparison of ChatGPT generated content and manual content indicates promising results that encourage using LLMs in the adaptive interfaces design process.