Problem reframing is a designerly activity where alternative perspectives are created to recast what a stated design problem is about. Generating alternative problem frames is challenging because it requires devising novel and useful perspectives that fit the given problem context. Large language models (LLMs) could assist this activity with their generative capability. However, it is not clear if they can help designers produce high-quality frames. Therefore, we asked if there are benefits to working with LLMs. To this end, we compared three ways of using LLMs (𝑁 = 280): 1) free-form, 2) direct generation, and 3) a structured approach informed by a theory of reframing. We found that using LLMs does not help improve the quality of problem frames. Rather, using LLMs increases the competence gap between experienced and inexperienced designers. Inexperienced designers also perceived lower agency when working with LLMs. We conclude that there is no benefit to using LLMs in problem reframing and discuss possible causes for this lack of effect.

People can generate high-quality ideas by building on each other’s ideas. By enabling individuals to contribute their ideas at their own comfortable time and method (i.e., asynchronous ideation), they can deeply engage in ideation and improve idea quality. However, running asynchronous ideation faces a practical constraint. Whereas trained human facilitators are needed to guide effective idea exchange, they cannot be continuously available to engage with individuals joining at varying hours. In this paper, we ask how chatbots can be designed to facilitate asynchronous ideation. For this, we adopted the guidelines found in the literature about human facilitators and designed two chatbots: one provides a structured ideation process, and another adapts the ideation process to individuals’ ideation performance. We invited 48 participants to generate and select ideas by interacting with one of our chatbots and invited an expert facilitator to review our chatbots. We found that both chatbots can guide users to build on each other’s ideas and converge them into a few satisfying ideas. However, we also found the chatbots’ limitations in social interaction with collaborators, which only human facilitators can provide. Accordingly, we conclude that chatbots can be promising facilitators of asynchronous ideation, but hybrid facilitation with human facilitators would be needed to address the social aspects of collaborative ideation.

One barrier to deeper adoption of user-research methods is the amount of labor required to create high-quality representations of collected data. Trained user researchers need to analyze datasets and produce informative summaries pertaining to the original data. While Large Language Models (LLMs) could assist in generating summaries, they are known to hallucinate and produce biased responses. In this paper, we study human--AI workflows that differently delegate subtasks in user research between human experts and LLMs. Studying persona generation as our case, we found that LLMs are not good at capturing key characteristics of user data on their own. Better results are achieved when we leverage human skill in grouping user data by their key characteristics and exploit LLMs for summarizing pre-grouped data into personas. Personas generated via this collaborative approach can be more representative and empathy-evoking than ones generated by human experts or LLMs alone. We also found that LLMs could mimic generated personas and enable interaction with personas, thereby helping user researchers empathize with them. We conclude that LLMs, by facilitating the analysis of user data, may promote widespread application of qualitative methods in user research. 

This paper describes a lab demo by the User Interfaces group at Aalto University. The demo allows attendees to interactively experience recent research prototypes aiming to facilitate designers’ creative and problem-solving capabilities in user interface (UI) design. Empirical work on designers suggests that UI design is challenging, partially because of the presence of very large design spaces, multiple and ill-defined objectives, design fixation and biases, as well as multiple requirements that need to to kept in mind. At the exhibition, members of the lab provide live demonstrations of six computational features, with a special focus on plug-ins created for Figma, a popular UI design tool. The demos draw from the group’s latest research published at HCI conferences. They demonstrate how to interactively exploit machine learning methods ranging from deep nets to Bayesian inference and NLP. We also present our design approach and provide a summary of findings from empirical evaluations with designers.

People can generate more innovative ideas when they collaborate with one another, collectively exploring ideas and exchanging viewpoints. Advancements in artificial intelligence have opened up new opportunities in people’s creative activities where individual users ideate with diverse forms of AI. For instance, AI agents and intelligent tools have been designed as ideation partners that provide inspiration, suggest ideation methods, or generate alternative ideas. However, what AI can bring to collaborative ideation among a group of users has not been fully understood. Compared to ideating with individuals, ideating with multiple users would require understanding users’ social interaction, transforming individual efforts into a group effort, and—in the end—making users satisfied that they collaborated with other group members. This workshop aims to bring together a community of researchers and practitioners to explore the integration of AI in human-human collaborative ideation. The exploration will center around identifying the potential roles of AI as well as the process and form of collaborative ideation, considering what users want to do with AI or humans.

Consensus-building is an essential process for the success of co-design projects. To build consensus, stakeholders need to discuss conflicting needs and viewpoints, converge their ideas toward shared interests, and grow their willingness to commit to group decisions. However, managing group discussions is challenging in large co-design projects with multiple stakeholders. In this paper, we investigate the interaction design of a chatbot that can mediate consensus-building conversationally. By interacting with individual stakeholders, the chatbot collects ideas to satisfy conflicting needs and engages stakeholders to consider others’ viewpoints, without having stakeholders directly interact with each other. Results from an empirical study in an educational setting (N = 12) suggest that the approach can increase stakeholders’ commitment to group decisions and maintain the effect even on the group decisions that conflict with personal interests. We conclude that chatbots can facilitate consensus-building in small-to-medium-sized projects, but more work is needed to scale up to larger projects.

In this study, we investigated how users work with a tablet in a non-desk setting. While portable computing devices have enabled ‘work anywhere’, few furniture and user interface has been designed for working in non-desk settings. In a co-exploration study, participants (n = 20) performed three tablet activities (video watching, typing, and drawing) on a configurable sofa. Using multiple cushions, the participants iteratively explored comfortable sitting as well as lying postures in diverse body orientations. The result showed a variety of postures and support configurations for the comfort of working in a non-desk setting. Unlike working a ta conventional desk setting, the body parts supported each other as well as a tablet, and preferred postures were unique to each activity. By systematically analyzing and categorizing postures, we uncovered new design opportunities for furniture and interactive systems that do not deal with a traditional desk setting. 

We report on our experiments to fabricate soft, functional and furniture size objects from PE foam sheets. This material is desirable because it is flexible, lightweight, widely available in a variety of thicknesses, and could be made out of sugar cane. We present a set of unique joining mechanisms that exploit the flexibility and do not use adhesive or fasteners. We show how to program softness in meta structures to avoid the use of multiple materials. Finally, we demonstrate a number of examples and discuss the applicability for prototyping as well as customization in deploying the design. 

While virtual objects are likely to be a part of future interfaces, we lack knowledge of how the dynamic position of virtual objects influences users’ posture. In this study, we investigated users’ posture change following the unobtrusive and swift motions of a content window in virtual reality (VR). In two perception studies, we estimated the perception threshold on undetectable slow motions and displacement during an eye blink. In a formative study, we compared users’ performance, posture change as well as subjective responses on unobtrusive, swift, and no motions. Based on the result, we designed concept applications and explored potential design space of moving virtual content for unobtrusive posture change. With our study, we discuss the interfaces that control users and the initial design guidelines of unobtrusive posture manipulation.

In recent years, there has been an increasing amount of Collaborative Augmented Reality (CAR) experiences, classifiable by the deployed scale and the fidelity of the experience. In this paper, we create HoloRoyale, the first large scale high fidelity (LSHF) CAR experience. We do this by first exploring the LSHF CAR design space, drawing on technical implementations and design aspects from AR and video games. We then create and implement a software architecture that improves the accuracy of synchronized poses between multiple users. Finally, we apply our target experience and technical implementation to the explored design space. A core design component of HoloRoyale is the use of visual repellers as crowd control elements to guide players away from undesired areas. To evaluate the effectiveness of the employed visual repellers in a LSHF CAR context we conducted a user study, deploying HoloRoyale in a 12.500 m2 area. The results from the user study suggest that visual repellers are effective crowd control elements that do not significantly impact the user’s overall immersion. Overall our main contribution is the exploration of a design space, discussing several means to address the challenges of LSHF CAR, the creation of a system capable of LSHF CAR interactions along with an experience that has been fitted to the design space, and an indepth study that verifies a key design aspect for LSHF CAR. As such, our work is the first to explore the domain of LSHF CAR and provides insight into designing experiences in other AR domains. 

Prolonged static and unbalanced sitting postures during computer usage contribute to musculoskeletal discomfort. In this paper, we investigated the use of a very slow moving monitor for unobtrusive posture correction. In a first study, we identified display velocities below the perception threshold and observed how users (without being aware) responded by gradually following the monitor's motion. From the result, we designed a robotic monitor that moves imperceptible to counterbalance unbalanced sitting postures and induces posture correction. In an evaluation study (n=12), we had participants work for four hours without and with our prototype (8 in total). Results showed that actuation increased the frequency of non-disruptive swift posture corrections and significantly reduced the duration of unbalanced sitting. Most users appreciated the monitor correcting their posture and reported less physical fatigue. With slow robots, we make the first step toward using actuated objects for unobtrusive behavioral changes. 

In this paper, we explored the application of human factor guidelines in personal fabrication. This is useful for several Do-It-Yourself (DIY) scenarios, including users adjusting workstation configurations or designing a desk to fit a single person. We identified a dependency map between the user's anthropometrics, ergonomic pose recommendations, and design dimensions. Based on this, we developed situated and interactive guidelines to assist users in design applications. We applied these guidelines in a Virtual Reality (VR) system that lets users customize their desk and provides real-time feedback and feedforward on pose and design. We evaluated the system with six participants, had each one design a personal desk, fabricated their desks, and let them work on their desks for four hours. The design and evaluation contribute to fabrication tools as it helped users be aware of their pose and ergonomic knowledge, and design for their bodies and needs. 

Food fabrication offers a new dimension to home cooking. We see the design challenge not in automating cooking tasks, but in augmenting the tangible experience, skill building and enjoyment of baking. As an example of such augmentation, we present a novel concept for designing and fabricating roll cakes with custom cross-section graphics.

Roll cakes are made by rolling a flat piece of cake into a spiral. In our application, users draw the cross section image of their cake and we calculate a printable template as a guide to color the unrolled cake. Users mix colored batter and use a custom 3D printed nozzle to arrange the batter on the template.

After baking the batter in the oven, users simply roll it into a roll cake and magically their design is shown on the cross-section.

We identified and solved the key difficulties in making graphics such as a consistent layer thickness and aligning the graphics in the spiral. With Rolling Graphics, we expand the potential of food printing with custom graphics and potentially, custom tastes.

The position and orientation of a monitor affects users' behavior at their desk. In this study, we explored and designed six types of interactions between an actuated monitor and users to induce posture changes. We built a virtual monitor that simulates the motions of an actuated monitor and slowly moved in the opposite direction of unbalanced sitting postures. We conducted an explorative study with eight participants. The study showed participants' responses and step by step posture changes toward balanced sitting postures. As contribution, we share considerations for designing monitor actuation that induce posture intervention. 

Level editors let end-users create custom levels and content within a given video game. In this paper, we explore the concept and design of Augmented reality game level editors. These new types of editors are not only spatial and embodied, but also situated, as they enable users to tailor games to the unique characteristics and emotional value of their own space.

We present the design and implementation of a prototype level editor that runs on the Microsoft HoloLens. The editor enables users to add virtual content in their homes and add interactions through spatial trigger-action game-logic programming. We had pairs of students create games with the prototype and play each other's games. They reported that games are fun to make, play, and watch others play. Based on the design and evaluation, we propose guidelines for Augmented reality game-authoring tools for end users.

In this paper, we investigate the use of Augmented Reality for users designing together. We present a design application that runs on multiple synchronized and spatially aware tablets to support couples making interior decisions in and for their future living room. Based on the prior art into collaborative design, we suggest a novel design interface that deals with situated design and supports virtual workspaces. We asked six couples to design together with our prototype and analyzed their design process, the roles they took, and how they communicated. The results suggest that the social practice of couples designing in and for their home differs from professional design teams and involves more than just positioning furniture in space. We use the design, the prototype and the study to discuss implications for spatial in-situ tools concerning intimacy, collaboration, and design process. The findings are useful for future applications that deal with collaborative applications for casual users.