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.

In order to gather data from the signing deaf community, efforts have been made to create online surveys in American Sign Language (ASL), despite a lack of user studies and UX/UI design guidelines informing the development of online survey tools featuring ASL. In this paper, we present SL-Surveys, an ASL-centric survey tool prototype showcasing a set of potential designs for multiple-choice, scalar, and multi-select questions. SL-Surveys was developed in an iterative process expressly for an exploratory think-aloud study investigating user experiences and perceptions of the designs. This preliminary study was conducted with seven deaf ASL-signing participants using a computer. The new design process, prototypes, user study and results make important strides towards a future where designs are not constrained by existing standards and practices based on written languages.

Students are often tasked in engaging with activities where they have to learn skills that are tangential to the learning outcomes of a course, such as learning a new software. The issue is that instructors may not have the time or the expertise to help students with such tangential learning. In this paper, we explore how AI-generated feedback can provide assistance. Specifically, we study this technology in the context of a constructionist curriculum where students learn about experimental research through the creation of a gamified experiment. The AI-generated feedback gives a formative assessment on the narrative design of student-designed gamified experiments, which is important to create an engaging experience. We find that students critically engaged with the feedback, but that responses varied among students. We discuss the implications for AI-generated feedback systems for tangential learning.

Questionnaires are fundamental learning and research tools for gathering insights and information from individuals, and now can be created easily using online tools. However, existing resources for creating questionnaires are designed for written languages (e.g. English) and do not support sign languages (e.g. American Sign Language). Sign languages (SLs) have unique visual characteristics that do not fit into user interface paradigms designed for written, text-based languages. Through a series of formative studies with the ASL signing community, this paper takes steps towards understanding the viability, potential benefit, challenges, and user interest in SL-centric surveys, a novel approach for creating questionnaires that meet the needs of deaf individuals using sign languages, without obligatory reliance on a written language to complete a questionnaire.

Recent work has investigated the construction of touch-sensitive knitted fabrics, capable of being manufactured at scale, and having only two connections to external hardware. Additionally, several sensor design patterns and application prototypes have been introduced. Our aim is to start shaping the future of this technology according to user expectations. Through a formative focus group study, we explore users’ views of using these fabrics in different contexts and discuss potential concerns and application areas. Subsequently, we take steps toward addressing relevant questions, by first providing design guidelines for application designers. Furthermore, in one user study, we demonstrate that it is possible to distinguish different swipe gestures and identify accidental contact with the sensor, a common occurrence in everyday life. We then present experiments investigating the effect of stretching and laundering of the sensors on their resistance, providing insights about considerations necessary to include in computational models.

Conducting human-centered research by, with, and for the ASL-signing Deaf community, requires rethinking current human-computer interaction processes in order to meet their linguistic and cultural needs and expectations. This paper highlights some key considerations that emerged in our work creating an ASL-based questionnaire, and our recommendations for handling them.