This paper proposes that the ability to generate diverse outputs in response to a single prompt is necessary for text-to-image models to become more effective creativity support tools. It formalises the problem of measuring the diversity of generated text and images, with an emphasis on interactive, exploratory use in open-ended and creative tasks. It suggests, motivated by research in the psychology of creativity, that diversity should sit alongside image quality and fit-to-prompt as critical measures in this setting. The paper adapts several diversity measures from the literature to this task, then explores how they compare to human diversity ratings. These evaluations show that algorithmic measures of diversity can be a useful proxy for human ratings, with both declining in accuracy as the difficulty of the task increases. The paper concludes with an exploratory qualitative analysis of the factors involved in human diversity judgments to guide future research in this emerging area.

This paper describes a mixed-methods usability study of seven diverse Self-Service Technologies (SSTs). SSTs mediate many of our everyday interactions with individuals, businesses, and government organizations. Parking meters, transport ticket machines, electric vehicle recharge points, and fast-food ordering kiosks are all likely familiar examples of this category of technology, promising convenient access to products and services. Despite their ubiquity, many SSTs suffer from severe usability issues, the nature of which have not been explored to date by the HCI community. This study evaluates the interactions between users and a broad sample of SSTs, details the usability issues that occurred, explores their connections and consequences, and presents a set of design considerations that may lead to their remediation.

In creativity support and computational co-creativity contexts, the task of discovering appropriate prompts for use with text-to-image generative models remains difficult. In many cases the creator wishes to evoke a certain impression with the image, but the task of conferring that succinctly in a text prompt poses a challenge: affective language is nuanced, complex, and very much influenced by the training trajectory of each specific AI model. In this work we introduce a method for generating images conditioned on desired affect, quantified using a psychometrically validated three-component approach, that can be combined with conditioning on text descriptions. We first train a neural network for estimating the affect content of text and images from semantic embeddings, and then demonstrate how this can be used to exert control over a variety of generative models. We show examples of how affect modifies the outputs, provide quantitative and qualitative analysis of its capabilities, and discuss possible extensions and use cases. We also show the capacity of our affect-guided generation to output images which re-frame or extend ideas in original ways that may not have been immediately apparent to the human prompt-writer.

Recent advances in text-conditioned generative models have provided us with neural networks capable of creating images of astonishing quality, be they realistic, abstract, or even creative. These models have in common that (more or less explicitly) they all aim to produce a high-quality one-off output given certain conditions, and in that they are not well suited for a creative collaboration framework. Drawing on theories from cognitive science that model how professional designers and artists think, we argue how this setting differs from the former and introduce CICADA: a Collaborative, Interactive Context-Aware Drawing Agent. CICADA uses a vector-based synthesis-by-optimisation method to take a partial sketch (such as might be provided by a user) and develop it towards a goal by adding and/or sensibly modifying traces. Given that this topic has been scarcely explored, we also introduce a way to evaluate desired characteristics of a model in this context by means of proposing a diversity measure. CICADA is shown to produce sketches of quality comparable to a human user's, enhanced diversity and most importantly to be able to cope with change by continuing the sketch minding the user's contributions in a flexible manner.

This paper presents an analysis of the user experience of Reframer, a novel human-AI drawing interface designed with the iterative and reflective nature of creativity in mind. Collaboration with Reframer occurs in real time, with the user and the system drawing together concurrently. This approach is inspired by theories of creativity as being more problem-framing than problem-solving, and contrasts with the automated one-shot end-to-end workflows of most generative AI models. A 12-participant qualitative exploratory study of the capabilities of our prototype is detailed, as well as a thematic analysis of user attitudes towards drawing with it. The paper then describes two modified prototypes and a second 32-participant comparative study revealing how interface variations evoke differences in user attitudes and experiences. It concludes by proposing a model that characterises the conditions under which users experience co-creative AI as a collaborator, rather than a non-agentive tool.

Over the past few years, rapid developments in AI have resulted in new models capable of generating high-quality images and creative artefacts, most of which seek to fully automate the process of creation. In stark contrast, creative professionals rely on iteration—to change their mind, to modify their sketches, and to re-imagine. For that reason, end-to-end generative approaches limit application to real-world design workflows. We present a novel human-AI drawing interface called Reframer, along with a new survey instrument for evaluating co-creative systems. Based on a co-creative drawing model called the Collaborative, Interactive Context-Aware Design Agent (CICADA), Reframer uses CLIP-guided synthesis-by-optimisation to support real-time synchronous drawing with AI. We present two versions of Reframer’s interface, one that prioritises emergence and system agency and the other control and user agency. To begin exploring how these different interaction models might influence the user experience, we also propose the Mixed-Initiative Creativity Support Index (MICSI). MICSI rates co-creative systems along experiential axes relevant to AI co-creation. We administer MICSI and a short qualitative interview to users who engaged with the Reframer variants on two distinct creative tasks. The results show overall broad efficacy of Reframer as a creativity support tool, but MICSI also allows us to begin unpacking the complex interactions between learning effects, task type, visibility, control, and emergent behaviour. We conclude with a discussion of how these findings highlight challenges for future co-creative systems design.

Choosing what to eat requires navigating a large volume of information and various competing factors. While recommendation systems are an effective approach to assist users with this culinary decision-making, they typically prioritise similarity to a query or user profile to give relevant results. This can expose users to an increasingly narrow band of phenomena, which could compromise dietary diversity, a factor in dietary quality. We designed Q-Chef, which combines a recipe recommendation system with a personalised model of surprise, and conducted a study to identify if surprise-eliciting recipes affect food decisions. Our study utilises a rigorous thematic analysis with over 40 participants to explore how computational models of surprise influence recipe choice. We also explored how these factors differed when people were presented with “surprising-yet-tasty” recipes, as opposed to just “tasty” recipes, and identified that being presented with surprising choices is more likely to elicit situational interest and prompt reflection on choices. We conclude with a set of suggestions for the design of future surprise-eliciting recipe systems.

This paper presents and evaluates a new method for inspiring creativity in a co-creative design system. The method uses a computational model of aconceptual shift based on clustering of deep features from a database of sketches. The co-creative sketching tool maps a user's sketch to a sketch of a distinct category that has high, medium, or low visual and semantic similarity. We hypothesize that the degree of similarity between the user's and the system's sketches is associated with a range of cognitive models of creativity in a design context. We report on the findings of an empirical study that analyzes different design scenarios in which the user sketches in response to a proposed conceptual shift. The findings show that how similar the computational agent's sketch is to the user's original sketch is related to the presence of three types of design creativity in the user's response: combinatorial, exploratory, and transformational.

Our natural tendency to be curious is increasingly important now that we are exposed to vast amounts of information. We often cope with this overload by focusing on the familiar: information that matches our expectations. In this paper we present a framework for interactive serendipitous information discovery based on a computational model of surprise. This framework delivers information that users were not actively looking for, but which will be valuable to their unexpressed needs. We hypothesize that users will be surprised when presented with information that violates the expectations predicted by our model of them. This surprise model is balanced by a value component which ensures that the information is relevant to the user. Within this framework we have implemented two surprise models, one based on association mining and the other on topic modeling approaches. We evaluate these two models with thirty users in the context of online health news recommendation. Positive user feedback was obtained for both of the computational models of surprise compared to a baseline random method. This research contributes to the understanding of serendipity and how to "engineer" serendipity that is favored by users.

The concept of surprise is central to human learning and development. However, compared to accuracy, surprise has received little attention in the IR community, yet it is an essential component of the information seeking process. This workshop brings together researchers and practitioners of IR to discuss the topic of computational surprise, to set a research agenda, and to examine how to build datasets for research into this fascinating topic. The themes in this workshop include discussion of what can be learned from some well-known surprise models in other fields, such as Bayesian surprise; how to evaluate surprise based on user experience; and how computational surprise is related to the newly emerging areas, such as fake news detection, computational contradiction, clickbait detection, etc.

This paper explores how participants constructed and re-constructed their relationship with an interactive art installation. The piece, textit{the willful marionette}, was developed in collaboration between artists and researchers. It explores the dynamics of non-verbal communication by building (from a scanned image of a human figure) a stringed marionette that responds to human movement. The intent was to challenge participants' expectations about communication, intelligence, emotion and the social role of the body. We show that participants' descriptions of their interactions vary along two axes: whether they or the marionette was perceived as leading the interaction, and whether they constructed a social or a technical mindset. We explore these differences using semi-structured interviews and a mix of qualitative and quantitative methods. We then present some implications for the design of both goal-directed and expressive embodied intelligent systems. textit{the willful marionette} has since been acquired by the Smithsonian American Art Museum as an example of cutting-edge art that deals with contemporary issues of machine intelligence and the social role of our bodies.

This paper presents a cognitive model of goal formulation in designing that is triggered by surprise. Cognitive system approaches to design synthesis focus on generating alternative designs in response to design goals or requirements. Few existing systems provide models for how goals change during designing, a hallmark of creative design in humans. In this paper we present models of surprise and reformulation as metacognitive processes that transform design goals in order to explore surprising regions of a design search space. The model provides a system with specific goals for exploratory behaviour, whereas previous systems have modelled exploration and novelty-seeking abstractly. We use observed designs to construct a probabilistic model that represents expectations about the design domain, and then reason about the unexpectedness of new designs with that model. We implement our model in the domain of culinary creativity, and demonstrate how the cognitive behaviors of surprise and problem reformulation can be incorporated into design reasoning.