ViseGPT: Towards Better Alignment of LLM-generated Data Wrangling Scripts and User PromptsLarge language models (LLMs) enable the rapid generation of data wrangling scripts based on natural language instructions, but these scripts may not fully adhere to user-specified requirements, necessitating careful inspection and iterative refinement. Existing approaches primarily assist users in understanding script logic and spotting potential issues themselves, rather than providing direct validation of correctness. To enhance debugging efficiency and optimize the user experience, we develop ViseGPT, a tool that automatically extracts constraints from user prompts to generate comprehensive test cases for verifying script reliability. The test results are then transformed into a tailored Gantt chart, allowing users to intuitively assess alignment with semantic requirements and iteratively refine their scripts. Our design decisions are informed by a formative study (N=8) that explores user practices and challenges. We further evaluate the effectiveness and usability of ViseGPT through a user study (N=18). Results indicate that ViseGPT significantly improves debugging efficiency for LLM-generated data-wrangling scripts, enhances users’ ability to detect and correct issues, and streamlines the workflow experience.2025JZJiajun Zhu et al.Human-LLM CollaborationExplainable AI (XAI)Interactive Data VisualizationUIST
Conversations With The Stressed Body: Facilitating Stress Self-Disclosure Among Adolescent Girls Through an Embodied Approach Adolescent girls face significant mental health challenges during their transition to adulthood, often experiencing heightened stress from various sources. While various interactive technologies for self-disclosure had been explored to support stress relief, little is known about how to encourage stress-related self-disclosure through an embodied approach. This study presents a co-design workshop centred on Embodied Probes—a series of artefacts and activities incorporating embodied methods and technologies. During the workshop, nine participants aged 15-18 engaged with their bodies, expressed bodily sensations through tangible means, and designed embodied prototypes tailored to their personal needs for stress perception and relief. The workshop revealed insights into somatic symptoms, sources, and coping strategies for stress among adolescent girls, as well as how embodied methods can support their stress self-disclosure. This paper contributes to the HCI community by offering design implications on leveraging embodied technologies to support self-disclosure for young women’s mental well-being.2025XSXinglin Sun et al.Full-Body Interaction & Embodied InputMental Health Apps & Online Support CommunitiesSleep & Stress MonitoringDIS
Remarkable Wireless Home NetworkingThis paper argues that wireless home networking has been critically underexamined and yet is an infrastructure that has come to configure everyday life. This design research inquiry offers a contemporary account of the domesticated Internet, with specific attention to the participants’ mundane practices (configurations, living with, and maintenance) of WiFi. Six rented households were remotely engaged through probe activities and three bespoke WiFi meters that allowed participants to measure otherwise invisible qualities of the network. It is found that while wireless opens the possibility of a home network for people who do not own their homes, the complex invisible dynamics of these networks are too inscrutable for even simple fixes to be made. The discussion closes with a question: if the services and infrastructures of the home become further entangled in the wireless network, might the problem of WiFi maintenance become an existential threat to a functioning home?2025DCDavid ChattingUbiquitous ComputingSmart Home Privacy & SecurityDIS
Exploring Legal Journeys in Family Justice Systems: Towards Relational Design Approaches to Advance Access to Justice for Domestic Abuse Survivors Access to justice includes mechanisms enabling people to have their voice heard, exercise their rights, and hold decision-makers accountable. This paper reports on an exploratory study aiming to understand Domestic Abuse (DA) survivors’ experiences of legal journeys through Family Court (FC) and Family Justice Systems (FJS) in England and Wales, and the potential for digital technologies to support their access to justice. We used qualitative methods including interviews and designed prompts to engage eight DA survivors and three Family Court professionals. Designed prompts enabled discussions and articulation of perceptions of socio-technical systems’ potential to support access to justice in FJS. Our findings describe challenges faced by survivors when accessing FJS, participating in proceedings, and living with outcomes stemming from Family Courts processes. We discuss opportunities for digital interventions in these contexts and provide design orientations for relational approaches to design research seeking to advance access to justice for DA survivors across legal jurisdictions.2025CCClara Crivellaro et al.Empowerment of Marginalized GroupsParticipatory DesignDIS
FretMate: ChatGPT-Powered Adaptive Guitar Learning AssistantLearning to play the guitar poses significant challenges for beginners, who often choose to practice alone to avoid the embarrassment of making mistakes in front of others. This isolation leads to a lack of timely feedback and encouragement, resulting in frustration and decreased motivation. Traditional learning methods fail to provide personalized and immediate support. To address these issues, we propose a GPT-powered guitar learning assistant, FretMate, that provides immediate error correction, personalized learning paths, and emotional support. The design was informed by formative interviews with six guitar instructors and six learners. We evaluated our assistant against the traditional self-guided practice in a controlled two-week study with 16 participants. Results showed that participants using FretMate improved in skill acquisition, engagement, and motivation compared to the control group. We discuss the po- tential of integrating conversational AI into instrument learning to provide personalized instruction and emotional engagement.2025XSXinhuan Shu et al.Intelligent Voice Assistants (Alexa, Siri, etc.)Generative AI (Text, Image, Music, Video)Intelligent Tutoring Systems & Learning AnalyticsIUI
Unveiling High-dimensional Backstage: A Survey for Reliable Visual Analytics with Dimensionality ReductionDimensionality reduction (DR) techniques are essential for visually analyzing high-dimensional data. However, visual analytics using DR often face unreliability, stemming from factors such as inherent distortions in DR projections. This unreliability can lead to analytic insights that misrepresent the underlying data, potentially resulting in misguided decisions. To tackle these reliability challenges, we review 133 papers that address the unreliability of visual analytics using DR. Through this review, we contribute (1) a workflow model that describes the interaction between analysts and machines in visual analytics using DR, and (2) a taxonomy that identifies where and why reliability issues arise within the workflow, along with existing solutions for addressing them. Our review reveals ongoing challenges in the field, whose significance and urgency are validated by five expert researchers. This review also finds that the current research landscape is skewed toward developing new DR techniques rather than their interpretation or evaluation, where we discuss how the HCI community can contribute to broadening this focus.2025HJHyeon Jeon et al.Seoul National University, Department of Computer Science and EngineeringInteractive Data VisualizationUncertainty VisualizationVisualization Perception & CognitionCHI
Exploring Alternative Socio-Technical Systems for Careful Data Work in Recovery ContextsNon-profits such as voluntary and community-based (VC) organisations are facing increasing pressures to engage in data work to sustain themselves. They face challenges with practices, information systems and tools associated with capturing data for supporting service provision. Most recently, researchers working with VC organisations have turned to Feminist and Care discourses to envision alternatives to current socio-technical systems whereby their values and purposes do not match with those of non-profits, consequently pulling the latter away from their socially driven mission. We report on a longitudinal, collaborative study with a UK-based mental health peer support organisation that created innovative tools as a means of navigating current pressures to practice data work for the quantification of mental health service provision. We present findings from interviews conducted with our community partner and share how recovery work has informed careful data practices, offering recommendations for supporting data work in mental health recovery.2025CCCaroline Claisse et al.Newcastle University, Open Lab, School of ComputingTechnology Ethics & Critical HCIDeveloping Countries & HCI for Development (HCI4D)Participatory DesignCHI
Leaky Cups: Tinkering with Hydrofeminist Temporalities for HCIThis paper offers new perspectives for More-Than-Human (MTH) design and Human-Computer-Interaction (HCI) by rethinking technoscientific logics of temporality. To do this, we draw on alternative logics such as Hydrofeminism, interlocutor and autobiographical accounts, and Leaky Cups—a set of willfully dysfunctional data-enabled artefacts that leak in response to local water data. In doing so, it repositions more-than-human agency not as a passive conduit merely mediating human experiences but as a force capable of creating change and ethics through non-progressivist care labor. By engaging with these ideas, this work critiques and disrupts normative assumptions about progress, openness, fluidity, and objectivity in MTH research and design, and presents productive tensions that challenge dominant temporal frameworks.2025CKCayla Key et al.University of Washington, Human Centered Design & Engineering; Northumbria University, School of DesignTechnology Ethics & Critical HCIDesign FictionCHI
Friend or Foe? Navigating and Re-configuring ``Snipers' Alley''In a 'digital by default’ society, essential services must be accessed online. This opens users to digital deception not only from criminal fraudsters but from a range of actors in a marketised digital economy. Using grounded empirical research from northern England, we show how supposedly 'trusted' actors, such as governments, (re)produce the insecurities and harms that they seek to prevent. Enhanced by a weakening of social institutions amid a drive for efficiency and scale, this has built a constricted, unpredictable digital channel. We conceptualise this as a ''snipers' alley''. Four key snipers articulated by participants' lived experiences are examined: 1) Governments; 2) Business; 3) Criminal Fraudsters; and 4) Friends and Family to explore how snipers are differentially experienced and transfigure through this constricted digital channel. We discuss strategies to re-configure the alley, and how crafting and adopting opportunity models can enable more equitable forms of security for all.2025ADAndrew Carl Dwyer et al.Royal Holloway, University of London, Information Security GroupPrivacy by Design & User ControlPrivacy Perception & Decision-MakingTechnology Ethics & Critical HCICHI
How the Role of Generative AI Shapes Perceptions of Value in Human-AI Collaborative WorkAs artificial intelligence (AI) continues to transform the modern workplace, generative AI (GenAI) has emerged as a prominent tool capable of augmenting work processes. Defined by its ability to create or modify content, GenAI differs significantly from traditional machine learning models that classify, recognize, or predict patterns from existing data. This study explores the role of GenAI in shaping perceptions of AI’s contribution and how these perceptions influence both creators’ internal assessments of their work and their anticipation of external evaluators’ assessments. Our research develops and empirically tests a structural model through a between-subjects experiment, revealing that the role GenAI plays in the work process significantly impacts perceived enhancements in work quality and effort relative to human input. Additionally, we identify a critical trade-off between fostering worker assessments of creativity and managing perceived external assessments of the work’s value.2025ASAaron Schecter et al.University of Georgia, Terry College of BusinessGenerative AI (Text, Image, Music, Video)Human-LLM CollaborationCHI
Seeking Inspiration through Human-LLM InteractionLarge language model (LLM) systems have been shown to stimulate creative thinking among creators, yet empirical research on whether users can seek inspiration in their everyday lives through these technologies is lacking. This paper explores which attributes of LLMs influence inspiration-seeking processes. Focusing on use cases of travel, cooking, and self-care, we interviewed 20 participants as they explored scenarios of these use cases using LLMs. Thematic analysis revealed that the vast data of LLMs inspires users with unexpected ideas, many of which were highly personalized, and inspired participants towards being motivated to act. Participants were also sensitive to the deficiencies of LLMs, and noted how ethical issues associated with these technologies could negatively impact them applying inspirational ideas into practice. We discuss the behavioral patterns of users actively seeking inspiration via LLMs, and provide design opportunities for LLMs that make the inspiration-seeking process more human-centric.2025XLXinrui Lin et al.Beijing Institute of Technology; University of EdinburghGenerative AI (Text, Image, Music, Video)Human-LLM CollaborationAI Ethics, Fairness & AccountabilityCHI
Beyond Bridging Divides: Examining the Goals of Digital Inclusion Practice in Post-Digital SocietiesThe widespread digitalisation of critical civic services in contexts of economic austerity, neoliberalism, and the COVID-19 pandemic, has renewed focus in HCI on interventions to enable digital access for populations considered ‘digitally excluded’. While digital inclusion (DI) practitioners play a critical role in this area, their perspectives remain under-explored in HCI. This paper reports on a series of asset-based engagements with digital inclusion practitioners in the North East of England. These engagements explored the values, assets, and needs comprising their practices and used these insights as design material to ideate strategies for future intervention. We contribute findings describing the complexities, contradictions, and diversity of digital inclusion practices and efforts. Based on these findings, we argue for a shift towards considering DI practice through the lens of care, and provide directions for future HCI research to support DI practitioners in doing care work.2025APAdam W Parnaby et al.Newcastle University, Open LabUniversal & Inclusive DesignDeveloping Countries & HCI for Development (HCI4D)CHI
RouteFlow: Trajectory-Aware Animated TransitionsAnimating objects’ movements is widely used to facilitate tracking changes and observing both the global trend and local hotspots where objects converge or diverge. Existing methods, however, often obscure critical local hotspots by only considering the start and end positions of objects' trajectories. To address this gap, we propose RouteFlow, a trajectory-aware animated transition method that effectively balances the global trend and local hotspots while minimizing occlusion. RouteFlow is inspired by a real-world bus route analogy: objects are regarded as passengers traveling together, with local hotspots representing bus stops where these passengers get on and off. Based on this analogy, animation paths are generated like bus routes, with the object layout generated similarly to seat allocation according to their destinations. Compared with state-of-the-art methods, RouteFlow better facilitates identifying the global trend and locating local hotspots while performing comparably in tracking objects' movements.2025DLDuan Li et al.Tsinghua UniversityInteractive Data VisualizationVisualization Perception & CognitionCHI
The Last JITAI? Exploring Large Language Models for Issuing Just-in-Time Adaptive Interventions: Fostering Physical Activity in a Prospective Cardiac Rehabilitation SettingWe evaluated the viability of using Large Language Models (LLMs) to trigger and personalize content in Just-in-Time Adaptive Interventions (JITAIs) in digital health. As an interaction pattern representative of context-aware computing, JITAIs are being explored for their potential to support sustainable behavior change, adapting interventions to an individual’s current context and needs. Challenging traditional JITAI implementation models, which face severe scalability and flexibility limitations, we tested GPT-4 for suggesting JITAIs in the use case of heart-healthy activity in cardiac rehabilitation. Using three personas representing patients affected by CVD with varying severeness and five context sets per persona, we generated 450 JITAI decisions and messages. These were systematically evaluated against those created by 10 laypersons (LayPs) and 10 healthcare professionals (HCPs). GPT-4-generated JITAIs surpassed human-generated intervention suggestions, outperforming both LayPs and HCPs across all metrics (i.e., appropriateness, engagement, effectiveness, and professionalism). These results highlight the potential of LLMs to enhance JITAI implementations in personalized health interventions, demonstrating how generative AI could revolutionize context-aware computing.2025DHDavid Haag et al.Ludwig Boltzmann Institute for Digital Health and Prevention; Austrian Institute of Technology, Digital Health Information Systems, Center for Health and BioresourcesHuman-LLM CollaborationMental Health Apps & Online Support CommunitiesContext-Aware ComputingCHI
How Do People Perceive Bundling? An ExperimentWe present an exploratory study on how people perceive visualizations of spatial social networks generated by edge bundling algorithms. Although these algorithms successfully minimize clutter in node-link diagrams, they do so through various methods that can sometimes create false connections between nodes. We conducted a qualitative experiment involving participants with technical expertise but no prior knowledge of edge bundling algorithms. Participants described their perceptions of both bundled and straight-line visualizations in open-ended tasks. Analysis of their annotations and transcripts revealed a general preference for bundled visualizations. However, when it came to false connections, participants tended to follow them in tightly bundled diagrams while also vocalizing that these drawings were more ambiguous. The routing of bundles influenced the perception of clusters and participants assigned more or fewer nodes to the clusters, depending on the routing of bundles. Participants' unfamiliarity with the dataset led them to use analogies to describe the bundled drawings, potentially adding perceived semantic meaning to the data.2025MWMarkus Wallinger et al.Technical University of Munich, Chair for Efficient AlgorithmsInteractive Data VisualizationUncertainty VisualizationVisualization Perception & CognitionCHI
Which linguistic cues make people fall for fake news? A comparison of cognitive and affective processingFake news on social media has large, negative implications for society. However, little is known about what linguistic cues make people fall for fake news and, hence, how to design effective countermeasures for social media. In this study, we seek to understand which linguistic cues make people fall for fake news. Linguistic cues (e.g., adverbs, personal pronouns, positive emotion words, negative emotion words) are important characteristics of any text and also affect how people process real vs. fake news. Specifically, we compare the role of linguistic cues across both cognitive processing (related to careful thinking) and affective processing (related to unconscious automatic evaluations). To this end, we performed a within-subject experiment where we collected neurophysiological measurements of 42 subjects while these read a sample of 40 real and fake news articles. During our experiment, we measured cognitive processing through eye fixations, and affective processing in situ through heart rate variability. We find that users engage more in cognitive processing for longer fake news articles, while affective processing is more pronounced for fake news written in analytic words. To the best of our knowledge, this is the first work studying the role of linguistic cues in fake news processing. Altogether, our findings have important implications for designing online platforms that encourage users to engage in careful thinking and thus prevent them from falling for fake news.2024BLBernhard Lutz et al.Session 3e: Trusting the Machine: Fake News. AI Decision-Making, and AuditingCSCW
Socio-digital rural resilience: An exploration of information infrastructures within and across rural villages during Covid-19Access to the internet and digital technology are reported determinants and enablers of social capital and community resilience. However, despite rural areas facing ecological, social, and economic uncertainties across the world, communication technologies and the design of civic technologies in HCI are not designed with the rural in mind. In this paper, we explore information infrastructures within and across rural villages in the UK focusing on the interplay between human, social, and technical infrastructures. We report on the existing communication practices, underlining the impacts of transitioning to digital communication technologies during the COVID-19 pandemic. Our findings point to the fragility of information infrastructure, the �civic duty� of bridging information and skills gaps, and the role of technology as a threat to social norms and disrupter of the �politics of the rural�. The work presented here has implications for Rural HCI researchers and designers interested in design from the rural.2024IJIan G. Johnson et al.Session 3b: Building Resilient CommunitiesCSCW
“The Gallery is Ephemeral”: Exploring the Intersection of Archival Practice and Technology in Artist-Run Initiatives. Artist-Run Initiatives (ARIs) are grassroots art galleries and project spaces that support artists by providing space for creative expression, experimentation, and exposure. While culturally important, these non-institutional collectives exist in precarious circumstances, with limited access to funding, heavy dependence on volunteers, and uncertainty in securing permanent space. We are particularly interested in how these issues intersect with ARIs’ uses of technology in archival practice. Through interviews with ARI committee members, our findings show intriguing perceptions of technological influence on archival practice, with concerns over reliance on cloud storage services, difficulties of digitising archival content, and how to present archived material on various digital platforms. We conclude with discussion on how future research might help support these communities to develop archival practices that are better suited to their practice.2024GMGareth McMurchy et al.Makerspace CultureMuseum & Cultural Heritage DigitizationC&C
Hostile Systems: A Taxonomy of Harms Articulated by Citizens Living with Socio-Economic DeprivationThere is increasing interest in how digitalisation variously impacts different socio-economic demographics’ ability to access, and realise benefits from, public services. Centring citizens’ lived experience in the identification of harms and benefits is critical for the evaluation of digital services, and more broadly for responsible innovation. Yet this poses significant challenges, particularly when engaging those living in precarious conditions. This paper reports on a study that engaged citizens living with poverty (n=76) to articulate harms arising from digitalisation in the context of an e-government social protection service. Interviews and surveys supported by speculative scenarios of ongoing changes helped surface and express citizen-centric harm characteristics within wider ecosystems before, during and after access, beyond a narrower service-lifecycle viewpoint. Drawing on the findings, we develop a taxonomy of harms and discuss how this can be utilised by HCI practitioners concerned with responsible innovation in digital welfare contexts.2024CWColin Watson et al.Newcastle UniversityInclusive DesignEmpowerment of Marginalized GroupsDeveloping Countries & HCI for Development (HCI4D)CHI
In Between Users and Developers: Serendipitous Connections and Intermediaries in Volunteer-Driven Open-Source Software DevelopmentTechnology plays a pivotal role in driving transformation through grassroots movements, which operate on a local scale while embracing a global perspective on sustainability. Consequently, research emerged within Sustainable HCI, aiming to derive design principles that can empower these movements to scale their impact. However, a notable gap exists in contributions when addressing scalability of large free and open-source software (FOSS) projects. This paper aims to present our endeavors as action-oriented researchers with the voluntary-driven Foodsharing.de movement, focusing on a local community, the open-source developers and their connections. Within a community of 585,000 users and only a few developers that is dedicated to save and share surplus food, we explore the concepts of ‘intermediary experience’. We also introduce the notion of ‘serendipitous connections’, highlighting the unintentional yet beneficial associations that can arise from the collaboration between developers and users.2024LJLeonie Jahn et al.University of SiegenSustainable HCICHI