In the creative practice of text-to-image (TTI) generation, images are synthesized from textual prompts. By design, TTI models always yield an output, even if the prompt contains unknown terms. In this case, the model may generate default images: images that closely resemble each other across many unrelated prompts. Studying default images is valuable for designing better solutions for prompt engineering and TTI generation. We present the first investigation into default images on Midjourney. We describe an initial study in which we manually created input prompts triggering default images, and several ablation studies. Building on these, we conduct a computational analysis of over 750,000 images, revealing consistent default images across unrelated prompts. We also conduct an online user study investigating how default images may affect user satisfaction. Our work lays the foundation for understanding default images in TTI generation, highlighting their practical relevance as well as challenges and future research directions.

Proliferation of misinformation is a globally acknowledged problem. Cognitive Inoculation helps build resistance to different forms of persuasion, such as misinformation. We investigate Conversational Inoculation, a method to help people build resistance to misinformation through dynamic conversations with a chatbot. We built a Web-based system to implement the method, and conducted a within-subject user experiment to compare it with two traditional inoculation methods. Our results validate Conversational Inoculation as a viable novel method, and show how it was able to enhance participants’ resistance to misinformation. A qualitative analysis of the conversations between participants and the chatbot highlighted adaptability, independence, trust and friction as the main factors affecting Conversational Inoculation. We discuss the opportunities and challenges of using Conversational Inoculation to combat misinformation. Our work contributes a timely investigation and a promising research direction in scalable ways to combat misinformation.

We are witnessing a novel era of creativity where anyone can create digital content via prompt-based learning (known as prompt engineering). This article investigates prompt engineering as a novel creative skill for creating AI art with text-to-image generation. In three consecutive studies, we explore whether crowdsourced participants can (1) discern prompt quality, (2) write prompts, and (3) refine prompts. We find that participants could evaluate prompt quality and crafted descriptive prompts, but they lacked style-specific vocabulary necessary for effective prompting. This is in line with our hypothesis that prompt engineering is a new type of skill that is non-intuitive and must first be acquired (e.g., through means of practice and learning) before it can be used at a level of high quality. Our studies deepen our understanding of prompt engineering and chart future research directions. We conclude by envisioning four potential futures for prompt engineering.

Image generation using generative artificial intelligence has become a popular activity. However, text-to-image generation—where images are produced from typed prompts—can be less engaging in public settings since the act of typing tends to limit interactive audience participation, thereby reducing its suitability for designing dynamic public installations. In this article, we explore body prompting as input modality for image generation in the context of public event settings. Body prompting extends interaction with generative AI beyond textual inputs to reconnect the creative act of image generation with the physical act of creating artworks. We implement this concept in an interactive art installation, Artworks Reimagined , designed to transform existing artworks via body prompting. We deployed the installation at an event with hundreds of visitors in a public and private setting. Our semi-structured interviews with a sample of visitors ( N = 79) show that body prompting was well-received and provides an engaging and fun experience. We present insights into participants’ experience of body prompting and AI co-creation and identify three distinct strategies of embodied interaction focused on re-creating, reimagining, or casual interaction. We provide valuable recommendations for practitioners seeking to design interactive generative AI experiences in museums, galleries, and public event spaces.

Text-guided synthesis of images has become enormously popular and online communities dedicated to text-to-image generation and art generated with Artificial Intelligence (AI) have emerged.While deep generative models can synthesise high-quality images and artworks from simple descriptive text prompts, practitioners of text-to-image generation typically seek to control the generative model's output by adding short key phrases ('modifiers') to the prompt.This paper identifies six types of prompt modifiers used by practitioners in the online text-toimage community based on a 3-month ethnographic study.The novel taxonomy of prompt modifiers provides researchers a conceptual starting point for investigating the practice of textto-image generation, but may also help practitioners of AI generated art improve their images.We further outline how prompt modifiers are applied in the practice of 'prompt engineering.' and discuss research opportunities of this novel creative practice in the field of Human-Computer Interaction (HCI).The paper concludes with a discussion of broader implications of prompt engineering from the perspective of Human-AI Interaction (HAI) in future applications beyond the use case of text-to-image generation and AI generated art.

Pilot studies are an essential cornerstone of the design of crowdsourcing campaigns, yet they are often only mentioned in passing in the scholarly literature. A lack of details surrounding pilot studies in crowdsourcing research hinders the replication of studies and the reproduction of findings, stalling potential scientific advances. We conducted a systematic literature review on the current state of pilot study reporting at the intersection of crowdsourcing and HCI research. Our review of ten years of literature included 171 articles published in the proceedings of the Conference on Human Computation and Crowdsourcing (AAAI HCOMP) and the ACM Digital Library. We found that pilot studies in crowdsourcing research (i.e., crowd pilot studies) are often under-reported in the literature. Important details, such as the number of workers and rewards to workers, are often not reported. On the basis of our findings, we reflect on the current state of practice and formulate a set of best practice guidelines for reporting crowd pilot studies in crowdsourcing research. We also provide implications for the design of crowdsourcing platforms and make practical suggestions for supporting crowd pilot study reporting.

Abstract Interactive public displays are versatile two-way interfaces between the digital world and passersby. They can convey information and harvest purposeful data from their users. Surprisingly little work has exploited public displays for collecting tagged data that might be useful beyond a single application. In this work, we set to fill this gap and present two studies: (1) a field study where we investigated collecting biometrically tagged video-selfies using public kiosk-sized screens, and (2) an online narrative transportation study that further elicited rich qualitative insights on key emerging aspects from the first study. In the first study, a 61-day deployment resulted in 199 video-selfies with consent to leverage the videos in any non-profit research. The field study indicates that people are willing to donate even highly sensitive data about themselves in public. The subsequent online narrative transportation study provides a deeper understanding of a variety of issues arising from the first study that can be leveraged in the future design of such systems. The two studies combined in this article pave the way forward towards a vision where volunteers can, should they so choose, ethically and serendipitously help unleash advances in data-driven areas such as computer vision and machine learning in health care.

Feedback is an important aspect of design education, and crowdsourcing has emerged as a convenient way to obtain feedback at scale. In this paper, we investigate how crowdsourced design feedback compares to peer design feedback within a design-oriented HCI class and across two metrics: perceived quality and perceived fairness. We also examine the perceived monetary value of crowdsourced feedback, which provides an interesting contrast to the typical requester-centric view of the value of labor on crowdsourcing platforms. Our results reveal that the students (N = 106) perceived the crowdsourced design feedback as inferior to peer design feedback in multiple ways. However, they also identified various positive aspects of the online crowds that peers cannot provide. We discuss the meaning of the findings and provide suggestions for teachers in HCI and other researchers interested in crowd feedback systems on using crowds as a potential complement to peers.

Spatial experience, or how humans experience a given space, has been a pivotal topic especially in urban-scale environments. On the human scale, HCI researchers have mostly investigated personal meanings or aesthetic and embodied experiences. In this paper, we investigate the human scale as an ensemble of individual spatial features. Through large-scale online questionnaires we first collected a rich set of spatial features that people generally use to characterize their surroundings. Second, we conducted a set of field interviews to develop a more nuanced understanding of the feature identified as most important: perceived safety. Our combined quantitative and qualitative analysis contributes to spatial understanding as a form of context information and presents a timely investigation into the perceived safety of human scale spaces. By connecting our results to the broader scientific literature, we contribute to the field of HCI spatial understanding.

Crowdsourcing platforms are increasingly being harnessed for creative work. The platforms' potential for creative work is clearly identified, but the workers' perspectives on such work have not been extensively documented. In this paper, we uncover what the workers have to say about creative work on paid crowdsourcing platforms. Through a quantitative and qualitative analysis of a questionnaire launched on two different crowdsourcing platforms, our results revealed clear differences between the workers on the platforms in both preferences and prior experience with creative work. We identify common pitfalls with creative work on crowdsourcing platforms, provide recommendations for requesters of creative work, and discuss the meaning of our findings within the broader scope of creativity-oriented research. To the best of our knowledge, we contribute the first extensive worker-oriented study of creative work on paid crowdsourcing platforms.

Web design is a complex and challenging task. It involves making many design decisions that materialise preconceived notions of user needs that may or may not be true. In this paper, we investigate supporting the co-design of a website with visual feedback elicited from the website's community of users. Website users can express their needs by re-arranging and modifying the website's layout and design. To explore and validate this idea, we present CrowdUI, a web-based tool that enables members of the community of a website to visually express their design improvement ideas, frustrations and needs, and to send this feedback to the person in charge of designing or maintaining the website. CrowdUI is validated in a study with 45 users of a popular social media and networking website. Second, our qualitative evaluation with 60 experienced web developers shows that CrowdUI is able to elicit diverse and meaningful feedback. Put together, our results suggest that CrowdUI's approach constitutes a productive setting for eliciting visual feedback from the user community as a complement to traditional ways of eliciting feedback and participatory design. Finally, based on our experiences, we discuss a design space for crowdsourced web design and provide design recommendations for similar future tools.

Online feedback systems have gained in popularity in recent years. These systems have the potential to provide vast amounts of feedback from the crowd. My dissertation explores how creative workers can be assisted in evaluating this crowdsourced feedback. I qualitatively explored and studied this issue in three different feedback systems. Future work will develop a framework for recommending feedback evaluation strategies for different feedback types in the context of creative work and potentially massive amounts of crowdsourced feedback.

The internet and digital technologies have had a strong influence on how art is created, distributed and perceived. Museums and art galleries, however, are still predominantly places of passive consumption of art. In our project, we explore new forms of communication and feedback between artists and their audience, mediated by public displays. In this work-in-progress paper, we present a situated feedback system for giving feedback on artworks in a public setting. We present a preliminary evaluation of the system with artists and potential audience on their reactions to the system and eight different types of feedback.

Crowdsourcing is a powerful approach for tapping into the collective insights of diverse crowds. Thus, crowdsourcing has potential to support designers in making sense of a design space. In this hands-on workshop, we will brainstorm and conceptualise new user interfaces and crowdsourcing systems for supporting designers in the design process. The workshop consists of developmental discussions of ideas contributed by the participants. In brainstorming and design sessions in groups, the participants will ideate new crowd-powered systems and user interfaces that support the designer's divergent and convergent thinking.

Go-along interviewing is an emerging qualitative research method for eliciting contextualised perspectives in which informants and observers conduct mobile interviews while navigating in real or imagined sites. This paper describes results of a pilot study that use virtual reality (VR) go-along interviews to explore university community members' (N=6) contextualized perceptions of urban habitat fragmentation due to new transportation infrastructure. Participants were immersed into the popular Google Street View and asked to navigate from the University campus to the city center. Along that route, construction sites featured in 360° images acted as prompts for discussing ecological change. Preliminary results indicate that VR go-along interviews are able to evoke emotions and inform a broad range of research questions with regards to both verbal and non-verbal feedback received from the informants.

Supporting creativity is a grand challenge in HCI. A critical component of creativity is the ability for divergent thinking, and divergent thinking can be fostered through looking at the problem through the lens of a different person, by assuming a role. Prior work found that assuming a role and affective stimulation with images may lead individuals to be more creative. In this work, we investigate the use of roles in stimulating the creativity of individuals in two complementary studies. In the first study, we implemented an online instrument for augmenting creativity with roles and images, and recruited crowd workers (n = 60) to complete a divergent thinking task while assuming a role. Interestingly, and in contrast to earlier findings, our analysis could not confirm the computational priming having an effect on the outcome of a small batch of creative tasks. In the second study, we observed the effect of roles on the ideation process of individuals when they reach an impasse in the flow of ideas. Our complementary studies highlight that adopting roles can help when one runs out of ideas, but this is not a silver bullet for improving divergent thinking, especially in online crowd-sourcing environments that are increasingly being used for experiments and data collection in behavioural science. Our work informs the design of future crowd-powered creativity support tools and contributes a timely case study to the body of literature in the growing field of creativity support online.