Figure 1: Our system supports nonlinear AI-assisted hypothesis exploration that balances breadth and depth of exploration.Using the node-link diagram shared representation and integrated information hint panels that display preliminary results and related work, a participant in our user study deeply explored a branch of hypotheses around gender income gaps, including a nuanced hypothesis about field-specific gender disparities in income (A); but also simultaneously kept track of the overall hypothesis space, and backtracked to explore other hypothesis branches around variations in income by marital status (B), such as post-divorce impacts on income.A more detailed version Figure 10 can be found in Appendix B.

Scholars must often make sense of vast amounts of complex and diverse scholarly information, much of which is not “senseable”: crucial information like questions, concepts, or assertions, along with key properties like truthlikeness or evocativeness, are primarily identified through effortful search or reasoning, rather than direct perception through the senses. In this pictorial, we explore how we might augment scholarly sensemaking by making the full range of scholarly information more senseable. First, we systematically reviewed systems for scholarly sensemaking, and enumerated key types of scholarly information and their properties. Then, we synthesized design patterns for materializing abstract information in modern artworks, and connected them with our enumerated scholarly information and properties to develop three novel conceptual designs for senseable scholarly sensemaking in immersive environments. Our work lays the foundation for a novel design framework for exploring future immersive environments for scholarly sensemaking.

Scholars often explore literature outside of their home community of study. This exploration process is frequently hampered by field-specific jargon. Past computational work often focuses on supporting translation work by removing jargon through simplification and summarization; here, we explore a different approach that preserves jargon as useful bridges to new conceptual spaces. Specifically, we cast different scholarly domains as different language-using communities, and explore how to adapt techniques from unsupervised cross-lingual alignment of word embeddings to explore conceptual alignments between domain-specific word embedding spaces.We developed a prototype cross-domain search engine that uses aligned domain-specific embeddings to support conceptual exploration, and tested this prototype in two case studies. We discuss qualitative insights into the promises and pitfalls of this approach to translation work, and suggest design insights for future interfaces that provide computational support for cross-domain information seeking.

The emergence of Generative Artificial Intelligence (GenAI) tools broadly, and Large Language Models (LLMs) specifically, are equipping introductory programming instructors with a whole new class of pedagogical tools. While GenAI certainly poses threats to time-honored instructional techniques, it also provides opportunities for new forms of instructional support. In this work, we introduce our strategy for configuring an LLM to serve as a ''rubber duck debugging'' coding assistant to help novice programmers when they encounter difficulties in programming assignments. The key contribution of this work is not in the idea of using LLMs for debugging itself (which has already been demonstrated elsewhere, e.g., [3]) but to demonstrate the ease, flexibility, and pedagogical potential of the strategy. In particular, through carefully crafted prompts and easily accessible platforms, rubber duck LLMs can assist learners with specific questions while also situating those questions alongside larger computer science concepts and computational thinking practices. This work contributes an easily replicated and model-agnostic instructional strategy that productively and responsibly leverages the power of LLMs to assist novice programmers in developing foundational programming skills.

Biologically Inspired Design (BID), or Biomimicry, is a problem-solving methodology that applies analogies from nature to solve engineering challenges. For example, Speedo engineers designed swimsuits based on shark skin. Finding relevant biological solutions for real-world problems poses significant challenges, both due to the limited biological knowledge engineers and designers typically possess and to the limited BID resources. Existing BID datasets are hand-curated and small, and scaling them up requires costly human annotations. In this paper, we introduce BARcode (Biological Analogy Retriever), a search engine for automatically mining bio-inspirations from the web at scale. Using advances in natural language understanding and data programming, BARcode identifies potential inspirations for engineering challenges. Our experiments demonstrate that BARcode can retrieve inspirations that are valuable to engineers and designers tackling real-world problems, as well as recover famous historical BID examples. We release data and code; we view BARcode as a step towards addressing the challenges that have historically hindered the practical application of BID to engineering innovation.

Analogies can be a powerful source of new ideas; however, creators often fail to recognize and harness potentially beneficial analogical leads, especially from other problem domains. In this paper, we introduce AnalogiLead, an interactive interface designed to reduce premature dismissal of analogies by facilitating playful exploration of analogical leads. Drawing on cognitive mechanisms of conceptual chunking and recombination, AnalogiLead scaffolds users to engage with meaningful chunks of problems and analogies and recombine them into inspiring brainstorming questions. In a within-subjects experiment, participants (N=23) who used AnalogiLead dismissed analogies 4x less often, with 12x fewer decision changes, compared to a baseline interface with no chunking or recombination. This reduction in premature dismissal was associated with 64% longer processing time. Through qualitative analysis of video and think-aloud data, we describe how the chunking and recombination mechanisms facilitated playful engagement with analogies. These findings highlight opportunities and challenges for improving analogical innovation through careful theory-driven design of interfaces for selecting analogical leads.

Interactive systems that facilitate exposure to examples can augment problem solving performance. However designers of such systems are often faced with many practical design decisions about how users will interact with examples, with little clear theoretical guidance. To understand how example interaction design choices affect whether/how people benefit from examples, we conducted an experiment where 182 participants worked on a controlled analog to an exploratory creativity task, with access to examples of varying diversity and presentation interfaces. Task performance was worse when examples were presented in a list, compared to contextualized in the exploration space or shown in a dropdown list. Example lists were associated with more fixation, whereas contextualized examples were associated with using examples to formulate a model of the problem space to guide exploration. We discuss implications of these results for a theoretical framework that maps design choices to fundamental psychological mechanisms of creative inspiration from examples.

The early days of HCI were marked by bold visions of hypertext as a transformative medium for augmented sensemaking, exemplified in systems like Memex, Xanadu, and NoteCards. Today, however, hypertext is often disconnected from discussions of the future of sensemaking. In this paper, we investigate how the recent resurgence in hypertext “tools for thought” might point to new directions for hypertext-augmented sensemaking. Drawing on detailed analyses of guided tours with 23 scholars, we describe hypertext-augmented use patterns for dealing with the core problem of revisiting and reusing existing/past ideas during scholarly sensemaking. We then discuss how these use patterns validate and extend existing knowledge of hypertext design patterns for sensemaking, and point to new design opportunities for augmented sensemaking.

Far domain analogies — relational comparisons between topics that seem very different on the surface, such as the solar system and an atom — can be a powerful source of new ideas. However, people struggle to benefit from them. We explore how bridging analogies, analogies that bridge between a knowledge anchor that is familiar to the problem solver, and a target analogy, can help innovators to benefit from far domain analogies. Utilizing a breadth first search for shortest paths between concepts on Wikipedia, we identified potential bridging analogies that connect a participant’s knowledge anchor to a far domain analogy. In a think aloud study, participants brainstormed on three design challenges, with only far analogies, or far analogies and bridging analogies tailored to their knowledge anchors. We observed that bridging analogies aided participants in producing more abstract solutions vs. more direct translation of the analogies in their solution.

Cross-domain analogical reasoning is a core creative ability that can be challenging for humans. Recent work has shown some proofs-of-concept of Large language Models’ (LLMs) ability to generate cross-domain analogies. However, the reliability and potential usefulness of this capacity for augmenting human creative work has received little systematic exploration. In this paper, we systematically explore LLMs capacity to augment cross-domain analogical reasoning. Across three studies, we found: 1) LLM-generated cross-domain analogies were frequently judged as helpful in the context of a problem reformulation task (median 4 out of 5 helpfulness rating), and frequently (∼ 80% of cases) led to observable changes in problem formulations, and 2) there was an upper bound of ∼ 25% of outputs being rated as potentially harmful, with a majority due to potentially upsetting content, rather than biased or toxic content. These results demonstrate the potential utility — and risks — of LLMs for augmenting cross-domain analogical creativity.

Professional designers often construct and explore conceptual representations (e.g.: design spaces) to help them reason about complex design situations and consider potential design pitfalls. However, it is often challenging, even for professional designers, to exhaustively consider the many pitfalls that might result from design activity. We present CausalMapper, a mixed-initiative system, that leverages a large language model (LLM) and a causal map representation to teach design students how to reason about the relationships between problems and solutions. Where creativity support tools often focus on ideating creative solutions, our mixed-initiative approach focuses on ideating ecosystems of solutions that holistically address a set of related problems. By leveraging the generative creativity of LLMs, designers are inspired to consider solutions and potential consequences that emerge when solutions are adopted. At the same time, leveraging the designers’ domain knowledge to account for and correct the biases inherent in LLMs. Through a case study, we demonstrate the functionality of this mixed-initiative system. The goal of this demo is to present a creativity support tool that is intended to teach design students to think more systematically by generating ideas that challenge their thinking rather just augmenting their creative potential.

Analogical reasoning, a process that integrates potential leads across domains and disciplines, has been proven to contribute to breakthrough innovations. Selecting the right analogical leads is crucial, as it determines the quality and effectiveness of the generated ideas. However, identifying relevant analogical leads can be challenging and may be missed due to premature rejection or design fixation. To address this problem, our system, "AnalogiLead", draws on the cognitive mechanisms of chunking and recombination as a medium of interaction for selecting beneficial analogies. Users interact with meaningful chunks or segments from a design problem and analogy, represented as interactive tiles called "magnets", and evaluate the analogies by recombining the "magnets" into brainstorming questions. These mechanisms are designed to foster playful and divergent exploration of analogical leads (vs. restrictive, relevance-based screening), to reduce premature rejection of analogical leads and foster more analogical innovations.

Participatory Design (PD) aims to promote inclusivity by involving users throughout the design process. However, Human-Computer Interaction (HCI) and social computing research have pointed to instances where PD as practiced can, paradoxically, be exclusive. We aim to understand some of the challenges that could lead to exclusivity in order to design more inclusive PD practices. To investigate this, we conducted interviews with ten expert PD practitioners based in the Global North whose focus is on inclusion. Synthesizing practitioners' accounts, we advance understandings of challenges surrounding: 1) instantiating shared spaces that empower partners; 2) developing common ground among stakeholders; and 3) balancing funding needs with open-ended PD. We contribute theoretical and empirical insights into these challenges and close by articulating potential implications for addressing these challenges to inclusion in PD.

Large repositories of products, patents and scientific papers offer an opportunity for building systems that scour millions of ideas and help users discover inspirations. However, idea descriptions are typically in the form of unstructured text, lacking key structure that is required for supporting creative innovation interactions. Prior work has explored idea representations that were either limited in expressivity, required significant manual effort from users, or dependent on curated knowledge bases with poor coverage. We explore a novel representation that automatically breaks up products into fine-grained functional aspects capturing the purposes and mechanisms of ideas, and use it to support important creative innovation interactions: functional search for ideas, and exploration of the design space around a focal problem by viewing related problem perspectives pooled from across many products. In user studies, our approach boosts the quality of creative search and inspirations, substantially outperforming strong baselines by 50-60%.

Analogies have been central to creative problem-solving throughout the history of science and technology. As the number of scientific articles continues to increase exponentially, there is a growing opportunity for finding diverse solutions to existing problems. However, realizing this potential requires the development of a means for searching through a large corpus that goes beyond surface matches and simple keywords. Here we contribute the first end-to-end system for analogical search on scientific articles and evaluate its effectiveness with scientists’ own problems. Using a human-in-the-loop AI system as a probe we find that our system facilitates creative ideation, and that ideation success is mediated by an intermediate level of matching on the problem abstraction (i.e., high versus low). We also demonstrate a fully automated AI search engine that achieves a similar accuracy with the human-in-the-loop system. We conclude with design implications for enabling automated analogical inspiration engines to accelerate scientific innovation.

Scholarly knowledge synthesis — the production of a novel conceptual whole such as an effective literature review or theory — is a critical yet consistently challenging subtask of research. We explore how managing the context of knowledge claims being synthesized, such as their production context or methodology, may be a critical under-supported subtask of synthesis in existing tools. Through in situ protocol analyses of researchers doing the work of synthesis, we studied how researchers capture contextual information in their notes and annotations, and how this varies across generic vs. specialized systems for synthesis. Our analysis revealed common process patterns of context capture, and qualitative differences in the nature of support for context capture across generic and specialized systems. Based on these findings, we discuss design implications for systems that aim to better support scholarly synthesis.

Visualization recommendation is important for exploratory analysis and making sense of the data quickly by automatically recommending relevant visualizations to the user. In this work, we propose the first end-to-end ML-based visualization recommendation system that leverages a large corpus of datasets and their relevant visualizations to learn a visualization recommendation model automatically. Then, given a new unseen dataset from an arbitrary user, the model automatically generates visualizations for that new dataset, derives scores for the visualizations, and outputs a list of recommended visualizations to the user ordered by effectiveness. We also describe an evaluation framework to quantitatively evaluate visualization recommendation models learned from a large corpus of visualizations and datasets. Through quantitative experiments, a user study, and qualitative analysis, we show that our end-to-end ML-based system recommends more effective and useful visualizations compared to existing state-of-the-art rule-based systems.

Scientific-style figures are commonly used on the web to present numerical information. Captions that tell accurate figure information and sound natural would significantly improve figure accessibility. In this paper, we present promising results on machine figure captioning. A recent corpus analysis of real-world captions reveals that machine figure captioning systems should start by generating accurate caption units. We formulate the caption unit generation problem as a controlled captioning problem. Given a caption unit type as a control signal, a model generates an accurate caption unit of that type. As a proof-of-concept on single bar charts, we propose a model, FigJAM, that achieves this goal through utilizing metadata information and a joint static and dynamic dictionary. Quantitative evaluations with two datasets from the figure question answering task show that our model can generate more accurate caption units than competitive baseline models. A user study with ten human experts confirms the value of machine-generated caption units in their standalone accuracy and naturalness. Finally, a post-editing simulation study demonstrates the potential for models to paraphrase and stitch together single-type caption units into multi-type captions by learning from data.

Design workshops are a popular means of including older adults in technology development. However, there are open questions around how to best scaffold this participation, particularly in supporting older adults to associate their designs with themselves, rather than designing for an "other older adult." By conducting workshops focusing on envisioning the future of internet of things (IoT) technologies at home, we provide an understanding of how older individuals participate in group activities to conceptualize technology for themselves. We find that at different stages of the design process, individuals shift in who they envision the end user of the technology: at first, they think about common older adult needs, then turn to designing for themselves. Individuals' attitudes towards technology also impact group dynamics along with final design ideas. Our discussion contributes to an understanding of how to support older adults in designing for themselves, new perspectives on aging-in-place technologies, and recommendations for configuring design workshops with older individuals.

Finding analogical inspirations in distant domains is a powerful way of solving problems. However, as the number of inspirations that could be matched and the dimensions on which that matching could occur grow, it becomes challenging for designers to find inspirations relevant to their needs. Furthermore, designers are often interested in exploring specific aspects of a product-- for example, one designer might be interested in improving the brewing capability of an outdoor coffee maker, while another might wish to optimize for portability. In this paper we introduce a novel system for targeting analogical search for specific needs. Specifically, we contribute an analogical search engine for expressing and abstracting specific design needs that returns more distant yet relevant inspirations than alternate approaches.

The availability of large idea repositories (e.g., patents) could significantly accelerate innovation and discovery by providing people inspiration from solutions to analogous problems. However, finding useful analogies in these large, messy, real-world repositories remains a persistent challenge for both humans and computers. Previous approaches include costly hand-created databases that do not scale, or machine-learning similarity metrics that struggle to account for structural similarity, which is central to analogy. In this paper we explore the viability and value of learning simple structural representations. Our approach combines crowdsourcing and recurrent neural networks to extract purpose and mechanism vector representations from product descriptions. We demonstrate that these learned vectors allow us to find analogies with higher precision and recall than traditional methods. In an ideation experiment, analogies retrieved by our models significantly increased people's likelihood of generating creative ideas.

Scientific discoveries are often driven by finding analogies in distant domains, but the growing number of papers makes it difficult to find relevant ideas in a single discipline, let alone distant analogies in other domains. To provide computational support for finding analogies across domains, we introduce SOLVENT, a mixed-initiative system where humans annotate aspects of research papers that denote their background (the high-level problems being addressed), purpose (the specific problems being addressed), mechanism (how they achieved their purpose), and findings (what they learned/achieved), and a computational model constructs a semantic representation from these annotations that can be used to find analogies among the research papers. We demonstrate that this system finds more analogies than baseline information-retrieval approaches; that annotators and annotations can generalize beyond domain; and that the resulting analogies found are useful to experts. These results demonstrate a novel path towards computationally supported knowledge sharing in research communities.

Online crowds can help infuse creativity into the design process, but traditional strategies for leveraging them, such as large-scale ideation platforms, require time and organizational effort in order to obtain results. We propose a new method for crowd-based ideation that simplifies the process by having smaller crowds join in-person ideators during synchronous creative sessions. Our system Crowdboard allows online crowds to provide real-time creative input during early-stage design activities, such as brainstorming or concept mapping. The system enables in-person ideators to develop ideas on a physical or digital whiteboard which is augmented with real-time creative input from online participants who see and hear a live broadcast of the meeting. We validate Crowdboard via two user studies in which dyads of in-person ideators brainstormed with the help of crowd ideators. Our studies suggest that Crowdboard can effectively enhance ongoing brainstorming sessions, but also revealed key challenges for how to better facilitate interactions among in-person and crowd ideators.

Collaborative ideation systems can help people generate more creative ideas by exposing them to ideas different from their own. However, there are competing theoretical views on whether and when such exposure is helpful. Associationist theory suggests that exposing ideators to ideas that are semantically far from their own maximizes novel combinations of ideas. In contrast, SIAM theory cautions that systems should offer far ideas only when ideators reach an impasse (a cognitive state in which they have exhausted ideas within a particular category), and offer near ideas during productive ideation (a cognitive state in which they are actively exploring ideas within a category), which maximizes exploration within categories. Our research compares these theoretical recommendations. In an online experiment, 245 participants generated ideas for a themed wedding; we detected and validated participants' cognitive states using a combination of behavioral and neuroimaging data. Receiving far ideas during productive ideation resulted in slower ideation and less within-category exploration, without significant benefits for novelty, compared to receiving no inspirations. Participants were also more likely to hit an impasse when receiving far ideas during productive ideation. These findings suggest that far inspirational ideas can harm creativity if received during productive ideation.

The availability of large idea repositories (e.g., the U.S. patent database) could significantly accelerate innovation and discovery by providing people with inspiration from solutions to analogous problems. However, finding useful analogies in these large, messy, real-world repositories remains a persistent challenge for either human or automated methods. Previous approaches include costly hand-created databases that have high relational structure (e.g., predicate calculus representations) but are very sparse. Simpler machine-learning/information-retrieval similarity metrics can scale to large, natural-language datasets, but struggle to account for structural similarity, which is central to analogy. In this paper we explore the viability and value of learning simpler structural representations, specifically, "problem schemas", which specify the purpose of a product and the mechanisms by which it achieves that purpose. Our approach combines crowdsourcing and recurrent neural networks to extract purpose and mechanism vector representations from product descriptions. We demonstrate that these learned vectors allow us to find analogies with higher precision and recall than traditional information-retrieval methods. In an ideation experiment, analogies retrieved by our models significantly increased people's likelihood of generating creative ideas compared to analogies retrieved by traditional methods. Our results suggest a promising approach to enabling computational analogy at scale is to learn and leverage weaker structural representations.

Large-scale idea generation platforms often expose ideators to previous ideas. However, research suggests people generate better ideas if they see abstracted solution paths (e.g., descriptions of solution approaches generated through human sensemaking) rather than being inundated with all prior ideas. Automated and semi-automated methods can also offer interpretations of earlier ideas. To benefit from sensemaking in practice with limited resources, ideation platform developers need to weigh the cost-quality tradeoffs of different methods for surfacing solution paths. To explore this, we conducted an online study where 245 participants generated ideas for two problems in one of five conditions: 1) no stimuli, 2) exposure to all prior ideas, or solution paths extracted from prior ideas using 3) a fully automated workflow, 4) a hybrid human-machine approach, and 5) a fully manual approach. Contrary to expectations, human-generated paths did not improve ideation (as meas-ured by fluency and breadth of ideation) over simply showing all ideas. Machine-generated paths sometimes significantly improved fluency and breadth of ideation over no ideas (although at some cost to idea quality). These findings suggest that automated sensemaking can improve idea generation, but we need more research to understand the value of human sensemaking for crowd ideation.

Online crowds are a promising source of new innovations. However, crowd innovation quality does not always match its quantity. In this paper, we explore how to improve crowd innovation with real-time expert guidance. One approach would for experts to provide personalized feed-back, but this scales poorly, and may lead to premature convergence during creative work. Drawing on strategies for facilitating face-to-face brainstorms, we introduce a crowd ideation system where experts monitor incoming ideas through a dashboard and offer high-level “inspirations” to guide ideation. A series of controlled experiments show that experienced facilitators increased the quantity and creativity of workers' ideas compared to unfacilitated workers, while Novice facilitators reduced workers' creativity. Analyses of inspiration strategies suggest these opposing results stem from differential use of successful inspiration strategies (e.g., provoking mental simulations). The results show that expert facilitation can significantly improve crowd innovation, but inexperienced facilitators may need scaffolding to be successful.

Prior work on creativity support tools demonstrates how a computational semantic model of a solution space can enable interventions that substantially improve the number, quality and diversity of ideas. However, automated semantic modeling often falls short when people contribute short text snippets or sketches. Innovation platforms can employ humans to provide semantic judgments to construct a semantic model, but this relies on external workers completing a large number of tedious micro tasks. This requirement threatens both accuracy (external workers may lack expertise and context to make accurate semantic judgments) and scalability (external workers are costly). In this paper, we introduce IdeaHound, an ideation system that seamlessly integrates the task of defining semantic relationships among ideas into the primary task of idea generation. The system combines implicit human actions with machine learning to create a computational semantic model of the emerging solution space. The integrated nature of these judgments allows IDEAHOUND to leverage the expertise and efforts of participants who are already motivated to contribute to idea generation, overcoming the issues of scalability inherent to existing approaches. Our results show that participants were equally willing to use (and just as productive using) IDEAHOUND compared to a conventional platform that did not require organizing ideas. Our integrated crowdsourcing approach also creates a more accurate semantic model than an existing crowdsourced approach (performed by external crowds). We demonstrate how this model enables helpful creative interventions: providing diverse inspirational examples, providing similar ideas for a given idea and providing a visual overview of the solution space.

Emerging online ideation platforms with thousands of example ideas provide an important resource for creative production. But how can ideators best use these examples to create new innovations? Recent work has suggested that not just the choice of examples, but also the timing of their delivery can impact creative outcomes. Building on existing cognitive theories of creative insight, we hypothesize that people are likely to benefit from examples when they run out of ideas. We explore two example delivery mechanisms that test this hypothesis: 1) a system that proactively provides examples when a user appears to have run out of ideas, and 2) a system that provides examples when a user explicitly requests them. Our online experiment (N=97) compared these two mechanisms against two baselines: providing no examples and automatically showing examples at a regular interval. Participants who requested examples themselves generated ideas that were rated the most novel by external evaluators. Participants who received ideas automatically when they appeared to be stuck produced the most ideas. Importantly, participants who received examples at a regular interval generated fewer ideas than participants who received no examples, suggesting that mere access to examples is not sufficient for creative inspiration. These results emphasize the importance of the timing of example delivery. Insights from this study can inform the design of collective ideation support systems that help people generate many high quality ideas.

Many crowd ideation systems seek to gather scores of ideas from people online. However, this often leads to many bad ideas and duplication. A dedicated facilitator who guides exploration of the solution space is a common and effective strategy for optimizing ideation in face-to-face brainstorming, but has not yet been explored in computer-supported crowd ideation. We introduce IdeaGens, a social ideation system for guided crowd brainstorming. IdeaGens divides the crowd into ideation and synthesis tasks, and enables efficient data-driven facilitation of the crowd’s ideation. This work can inform general strategies for shepherding the crowd to produce better results for complex collaborative tasks.