Conference Agenda

Reflection plays a vital role in the development of designers, enabling them to evaluate their experiences, enhance their learning, and foster professional growth. This research analyzed reflections of 56 design students, as part of graded coursework, using content and dictionary-based approaches (LIWC). Building on an existing model of reflection with eight components (experience, belief, difficulty, perspective, feeling, learning, intention, and descriptive) we identify, using descriptive statistics, the linguistic features associated with each component and correlate these to grades achieved. We distinguish two types of reflections associated with higher grades: those emphasizing personal experiences that we term holistic narrators, and those that focus on critical self-evaluation that we term in-depth explorers. Our results provide insights for design educators, guiding interventions to enhance critical thinking and self-reflection among design students. They also inform the development of automated tools to assess and enhance reflective practice in educational and design settings.

In an increasingly complex landscape, designers grapple with unprecedented uncertainty, often exacerbated by inherent biases and implicit assumptions. Utilizing Large Language Models (LLMs), our formative study introduces "Anticipate," a tool designed to interrogate these hidden presumptions and mitigate uncertainty. A subsequent study demonstrates that LLMs can critically challenge design ideas, elucidate underlying thought patterns, and expose biases, thereby preempting undesirable outcomes. Importantly, we employ specific input framing techniques to minimize the risk of LLM-induced biases and hallucinations in decision-making. Collectively, these methodologies aim to attenuate both designer and algorithmic biases, thereby mitigating the perpetuation of adverse societal trends.

In human-centered design (HCD) projects, designers select and use a variety of design methods in pursuit of a desired outcome. Given the prominence of method selection in designer behavior, what distinguishes a design team’s method selections from design method selection based on frequency or probability? To explore this question, we compare HCD methods suggested by the publicly-available large-language model, GPT-3.5, to 402 novice design team method selections over five offerings of a design projectbased learning course at a large public university. We observe that GPT-3.5 appears to represent design method knowledge held in method repositories like theDesignExchange well. We also observe that GPT-3.5’s method selection recommendations appear to poorly distinguish between HCD phases, and appear limited to highly specific aspects of HCD phases. These findings highlight the unique contribution of human design cognition in design decision-making relative to LLM’s, and herald the promise of human-AI teaming in design method selection.

This paper explores the ongoing and nonlinear nature of everyday group conversations afforded by a mobile messaging app. Understanding such interactions can facilitate the awareness of different viewpoints and the emergence of group decisions on elucidating design problems. The exploration is done by analyzing stakeholders' group chat conversations through the lens of small stories, which acknowledges overlooked aspects of everyday communication. Communicative interactions are increasingly relevant to participatory processes of coordinating knowledge, needs, and goals among multiple stakeholders in designing. Meanwhile, communication in goal-oriented workshops and interviews aims for an effective sense-making process and compels the definition of problem and solution. Such an arrangement for communication could constrain the stakeholder's agency to redefine the design problem upon ideating alternative solutions. Therefore, this paper aims to scrutinize a less structured and mundane communication setting and its significance on stakeholder agency to iteratively reconceive the problem at hand.

In new product development, engaging users in co-creation provides valuable opportunities for innovation by uncovering their latent needs. However, user knowledge is often tacit and difficult to express. This study considers Generative-Image-AI as a tool to facilitate communication between users and designers, and explores how it intervenes in the design process to facilitate meaningful design conversations. We proposed the conceptual design iteration process model for Generative-Image-AI intervention in the product conceptual design phase and conducted a workshop with six designer-user dyads. The results demonstrated the positive impact of Generative-Image-AI on design conversations by fostering continuous communication, expanding possibilities, and encouraging reflection and iteration. We also discussed the new challenges that Generative-Image-AI brought to design conversations. Overall, Generative-Image-AI enriches the co-creation design conversations. Our research contributes to the integration of AI in human-human collaboration processes and provides a new perspective and foundation for AI-supported participatory design conversations.

Designers deploy metaphors in various constructive ways but there is a challenge in noticing and selecting helpful metaphors to describe AI systems. Metaphors serve to highlight certain aspects of AI but their influence can be so potent that envisioning or discussing AI in alternative ways becomes challenging, with unwanted expectations, lazy tropes and hidden biases. Alternative metaphors help designers grasp distinctive qualities of AI and move past hidden assumptions. Hence, it is key to support designers in precise, plural and intentional metaphor use to grasp unique qualities of AI and explore its relationalities. We illustrate this through a selection of prototyping journeys in which metaphors directly shaped students’ design trajectories and allowed them to explore the relational, entangled complexities of AI systems. Finally, ‘metaphor gardening,' provides a series of recommendations for designers when designing AI with metaphors, which we hope can ultimately support a generative and responsible approach to AI technologies.