Balancing Efficiency and Empathy: Healthcare Providers' Perspectives on AI-Supported Workflows for Serious Illness Conversations in the Emergency DepartmentSerious Illness Conversations (SICs)—discussions about values and care preferences for patients with life-threatening illness—rarely occur in Emergency Departments (EDs), despite evidence that early conversations improve care alignment and reduce unnecessary interventions. We interviewed 11 ED providers to identify challenges in SICs and opportunities for technology support, with a focus on AI. Our analysis revealed a four-stage SIC workflow (identification, preparation, conduction, documentation) and barriers at each stage, including fragmented patient information, limited time and space, lack of conversational guidance, and burdensome documentation. Providers expressed interest in AI systems for synthesizing information, supporting real-time conversations, and automating documentation, but emphasized concerns about preserving human connection and clinical autonomy. This tension highlights the need for technologies that enhance efficiency without undermining the interpersonal nature of SICs. We propose design guidelines for ambient and peripheral AI systems to support providers while preserving the essential humanity of these conversations.2026MZMenglin Zhao et al.Northeastern UniversityAI-Assisted Decision-Making & AutomationMental Health Apps & Online Support CommunitiesTelemedicine & Remote Patient MonitoringCHI
"My Brother Is a School Principal, Earns About $80,000 Per Year... But When the Kids See Me, 'Wow, Uncle, You Have 1,500 Followers on TikTok!'": A Study of Blind TikTokers' Alternative Professional Development ExperiencesOne’s profession is an essential part of modern life. Traditionally, professional development has been criticized for excluding people with disabilities. People with visual impairments, for example, face disproportionately low employment rates, highlighting persistent gaps in professional opportunities. Recently, there has been growing research on social media platforms as spaces for more equitable career development approaches. In this paper, we present an interview study on the professional development experiences of 60 people with visual impairments on TikTok (also known as “BlindTokers”). We report BlindTokers’ goals, strategies, and challenges, supported by detailed examples and in-depth analysis. Based on the findings, we identified that BlindTokers’ practices reveal an alternative professional development approach that is more flexible, inclusive, personalized, and diversified than traditional models. Our study also extends professional development research by foregrounding emerging digital skills and proposing design implications to foster more equitable and inclusive professional opportunities.2026YLYao Lyu et al.University of MichiganSocial Platform Design & User BehaviorCognitive Impairment & Neurodiversity (Autism, ADHD, Dyslexia)Universal & Inclusive DesignCHI
PrivWeb: Unobtrusive and Content-aware Privacy Protection For Web AgentsWhile web agents gained popularity by automating web interactions, their requirement for interface access introduces privacy risks that are understudied, particularly from users' perspective. Through a formative study (N=15), we found that users frequently misunderstand agent data practices, and desire unobtrusive, transparent data management. To achieve this, we developed PrivWeb, a trusted add-on on web agents that utilizes a localized LLM to anonymize private information on interfaces based on user preferences. It employs a tiered delegation to balance automation and intrusiveness, using ambient notifications for low-sensitivity data and enforces a mandatory pause for high-sensitivity data. The user study (N=14) across travel, information retrieval, shopping, and entertainment tasks showed that PrivWeb enhances perceived privacy protection and trust compared to transparency-only baselines, without increasing cognitive load. Crucially, we identified user delegation strategies: they prefer to manually execute sensitive steps for high-sensitivity data, while granting agent access to low-sensitivity data.2026SZShuning Zhang et al.Tsinghua UniversityPrivacy by Design & User ControlPrivacy Perception & Decision-MakingHuman-LLM CollaborationCHI
Auditorily Embodied Conversational Agents: Effects of Spatialization and Situated Audio Cues on Presence and Social PerceptionEmbodiment can enhance conversational agents, such as increasing their perceived presence. This is typically achieved through visual representations of a virtual body; however, visual modalities are not always available, such as when users interact with agents using headphones or display-less glasses. In this work, we explore auditory embodiment. By introducing auditory cues of bodily presence — through spatially localized voice and situated Foley audio from environmental interactions — we investigate how audio alone can convey embodiment and influence perceptions of a conversational agent. We conducted a 2 (spatialization: monaural vs. spatialized) × 2 (Foley: none vs. Foley) within-subjects study, where participants (n=24) engaged in conversations with agents. Our results show that spatialization and Foley increase co-presence, but reduce users’ perceptions of the agent’s attention and other social attributes.2026YCYi Fei Cheng et al.Carnegie Mellon UniversityAffective Human-Computer DialogueSpatial Audio & 3D SoundAffective Feedback & Emotion Regulation InterfacesCHI
Navigating Safety and Technology: The Everyday Safety Labor of Transgender Black, Indigenous, and People of Color in the United StatesTechnologies like online support networks and safety apps hold promise for improving personal safety. However, these tools often fail to address the widespread violence against gender-diverse individuals, particularly transgender Black, Indigenous, and People of Color (TBIPOC) in the United States. To better understand technology's role in managing safety among TBIPOC individuals, we conducted 22 semi-structured interviews. We found that participants engaged in what we call safety labor, the emotional and cognitive work of managing misrecognition, assessing risk, and downplaying discomfort to maintain self-preservation. Visibly-trans participants faced greater vulnerability and tended to feel safer when their trans identity was not visible. Technology enabled sharing locations and rides, and sending coded messages. Findings highlight the need for tailored technologies that protect privacy and help TBIPOC individuals when they experience violence. Our research contributes a deeper understanding of TBIPOC experiences and informs technology development to promote TBIPOCs’ safety.2026DSDenny L Starks et al.University of MichiganPrivacy by Design & User ControlPrivacy Perception & Decision-MakingOnline Harassment & Counter-ToolsCHI
Understanding Gendered Experiences of Harassment Among Pakistani Young Adults Using Human-Centered Threat ModelingHarassment impacts the safety and well-being of young adults in Pakistan. Prior research has largely focused on women, often imposing external definitions of harm and overlooking how individuals themselves understand and respond to harassment. This study examines how Pakistani young adults define, experience, and cope with harassment. Drawing on 33 semi-structured interviews guided by a human-centered threat modeling framework, we surface context-specific threat models. Participants’ definitions of harassment were shaped by gender norms, religious values, and moral judgments. Women described harassment as a routine part of life, tied to public visibility, modesty norms. Men also reported harassment, though framed by different dynamics such as pressure to maintain control, avoid vulnerability, and conform to masculinity. Across participants, formal reporting pathways were viewed as untrustworthy or unsafe. Our findings highlight the need for interventions that reflect local definitions of harm, address relational adversaries, and support safety within sociocultural contexts.2026WUWarda Usman et al.Brigham Young UniversityOnline Harassment & Counter-ToolsGender & Race Issues in HCIEmpowerment of Marginalized GroupsCHI
The Burden of Bearing Witness: Digital Practices of Marginalized Social Media Users in High-Stakes Contexts Social media platforms and their governance policies often fail marginalized users in high-stakes contexts, including war, violent attacks, human rights violations, humanitarian crises, and situations of systemic oppression. Through interviews, autoethnography, and digital ethnography, this paper presents three case studies from Venezuela, Nigeria, and the United States to examine how marginalized populations engage with social media in non-normative ways. We analyze how platform design and policies intersect with participants’ identities, marginalization, and labor. Our central finding is that users’ urgent infrastructural and contextual needs are often overlooked, revealing structural flaws in social media design that mimic physical-world power asymmetries. In response, users develop innovative workarounds, engage in self-censorship, and adopt coping strategies, undertaking additional, often invisible, sociotechnical repair work that reinforces their precarity. To address these complex needs, we urge social media companies to collaborate with marginalized users to integrate alternative infrastructural features, such as emergency response tools and exit mechanisms for well-being.2026SKSena A. Kojah et al.University of MichiganContent Moderation & Platform GovernanceCyberbullying & Online HarassmentEmpowerment of Marginalized GroupsCHI
Dark Patterns Meet GUI Agents: LLM Agent Susceptibility to Manipulative Interfaces and the Role of Human OversightThe dark patterns, deceptive interface designs manipulating user behaviors, have been extensively studied for their effects on human decision-making and autonomy. Yet, with the rising prominence of LLM-powered GUI agents that automate tasks from high-level intents, understanding how dark patterns affect agents is increasingly important. We present a two-phase empirical study examining how agents, human participants, and human-AI teams respond to 16 types of dark patterns across diverse scenarios. Phase 1 highlights that agents often fail to recognize dark patterns, and even when aware, prioritize task completion over protective action. Phase 2 revealed divergent failure modes: humans succumb due to cognitive shortcuts and habitual compliance, while agents falter from procedural blind spots. Human oversight improved avoidance but introduced costs such as attentional tunneling and cognitive load. Our findings show neither humans nor agents are uniformly resilient, and collaboration introduces new vulnerabilities, suggesting design needs for transparency, adjustable autonomy, and oversight.2026JTJingyu Tang et al.University of Notre DameDark Patterns RecognitionHuman-LLM CollaborationAI-Assisted Decision-Making & AutomationCHI
Three Modalities, Two Design Probes, One Prototype, and No Vision: Experience-Based Co-Design of a Multi-modal 3D Data Visualization ToolThree-dimensional (3D) data visualizations, such as surface plots, are vital in STEM fields from biomedical imaging to spectroscopy, yet remain largely inaccessible to blind and low-vision (BLV) people. To address this gap, we conducted an Experience-Based Co-Design with BLV co-designers with expertise in non-visual data representations to create an accessible, multi-modal, web-native visualization tool. Using a multi-phase methodology, our team of five BLV and one non-BLV researcher(s) participated in two iterative sessions, comparing a low-fidelity tactile probe with a high-fidelity digital prototype. This process produced a prototype with empirically grounded features, including reference sonification, stereo and volumetric audio, and configurable buffer aggregation, which our co-designers validated as improving analytic accuracy and learnability. In this study, we target core analytic tasks essential for non-visual 3D data exploration: orientation, landmark and peak finding, comparing local maxima versus global trends, gradient tracing, and identifying occluded or partially hidden features. Our work offers accessibility researchers and developers a co-design protocol for translating tactile knowledge to digital interfaces, concrete design guidance for future systems, and opportunities to extend accessible 3D visualization into embodied data environments.2026SKSanchita S. Kamath et al.University of Illinois Urbana-ChampaignVisual Impairment Technologies (Screen Readers, Tactile Graphics, Braille)Interactive Data VisualizationMedical & Scientific Data VisualizationCHI
`I Know I Can Do the Job, It’s Just Putting It Down’: Using Personas as a Mirror to Identify StrengthsWork is increasingly shifting away from traditional full-time jobs toward more fragmented ways of working, like gig work and part-time jobs. Yet, employment platforms like LinkedIn often privilege those with traditional credentials and work histories, presenting barriers to those who possess little experience translating informal experiences into a format that such tools expect. To address this gap, we propose a narrative-based approach that enables individuals to recognize transferable skills and practice articulating them verbally and in writing via a group discussion setting. Through a participatory design workshop held in a public housing community, we demonstrate how a cultural-probe and persona-inspired activity can elicit self-reflection, enabling individuals to communicate their strengths. While prior HCI research has highlighted the critical need for reflection in the job search process, little work has been done to facilitate this reflection and translation into employment profiles. Our work addresses this call and informs new design directions for employment technologies.2026JHJulie Hui et al.University of MichiganParticipatory DesignPrototyping & User TestingJob Search & Employment SupportCHI
Safety With Community: Technologies of Care, Connection, Collective Safety, and Mutual Aid for Transgender Black, Indigenous, and People of Color (TBIPOC) Technology has the potential to enhance safety by supporting community-driven strategies. However, current safety technologies often narrowly frame safety as preventing violence, without incorporating the community-centered strategies essential to well-being for transgender, Black, Indigenous, and People of Color (TBIPOC). We conducted 22 interviews with TBIPOC individuals to understand their safety challenges, experiences navigating violence, and safety strategies. Our findings reveal that safety is not only the absence of harm but also the presence of trust, connection, collective care, and mutual aid. Participants emphasized survival resources like self-defense training and trans-specific spaces, alongside joy rooted in community and support. We argue that community is not separate from safety; it is its foundation. This work contributes fundamental knowledge about TBIPOCs’ experiences and design implications for technologies that affirm TBIPOC lives. Designing for TBIPOC safety requires shifting toward community-centered technologies and non-technological approaches that prioritize lived experiences, mutual aid, and collective joy.2026DSDenny L. Starks et al.University of MichiganEmpowerment of Marginalized GroupsTechnology Ethics & Critical HCICHI
Digital Infrastructural Resistance: Working Around Severe Telecommunication Disruptions in GazaDespite experiencing extensive losses in telecommunication infrastructure since October 2023, Gazans have managed to communicate with the outside world. How have they accomplished this? Through semi-structured interviews with 18 Gazan residents, this study examines how Gazans have perceived various interruptions and losses of electronic communication, how they responded and worked around communication limits, and why they persisted in communicating outside of Gaza. Our findings confirm previous results about communication under state-imposed telecom shutdowns, and also contribute new knowledge, given Gaza’s distinctive political and technological dynamic. We find that restrictions drove participants– who felt compelled to maintain contact – to perpetual technical improvisation, often toward pre-digital tools, varying by geography, available technology, and electrical power. Creative, subaltern networks such as Bluetooth meshes and street internet disrupted severe repression. Our participants discussed such activities as a response to the larger context of violence, and we conceptualize their efforts as "digital infrastructural resistance."2026GAGhadeer A. Awwad et al.University of MichiganSocial Media Information Dissemination in DisastersEmergency Communication & Early Warning SystemsVolunteer Coordination & Crowdsourced Disaster ReliefCHI
RealTwin: Concept Graph Representation and Grounding Framework for Reality-Preserving Digital Twin ReconstructionReconstructing realistic digital twins has become crucial as advances in mixed reality, metaverse, and robotics demand more accurate simulations for the physical world. Despite technical progress, building high-fidelity digital twins from a systematic and human-centered perspective remains underexplored. Drawing from the human processing model, we decompose human-centric reality into perception, motion, and cognition, and define a reality-preserving digital twin (RPDT) as a reconstruction integrating these dimensions. We present RealTwin, an attribute-graph-based representation and inference framework for RPDT. Leveraging the grounding capabilities of Multimodal Large Language Models (MLLMs), RealTwin chains AI tools to construct attribute graphs that faithfully encode real-world properties. We validate RealTwin through both technical evaluation, showing promising success in graph parsing and attribute inference, and a user study, assessing its applicability across diverse user groups. Enlightened by RealTwin, we discuss critical issues, including ecology, interaction space, and real-world adoption, for future end-to-end, fine-grained, and scalable digital twin reconstruction.2026ZLZisu Li et al.The Hong Kong University of Science and TechnologyImmersion & Presence ResearchMixed Reality WorkspacesHuman-LLM CollaborationCHI
From Use to Oversight: How Mental Models Influence User Behavior and Output in AI Writing AssistantsAI-based writing assistants are ubiquitous, yet little is known about how users’ mental models shape their use. We examine two types of mental models—functional or related to what the system does, and structural or related to how the system works—and how they affect control behavior—how users request, accept, or edit AI suggestions as they write—and writing outcomes. We primed participants (𝑁 = 48) with different system descriptions to induce these mental models before asking them to complete a cover letter writing task using a writing assistant that occasionally offered preconfigured ungrammatical suggestions to test whether the mental models affected participants’ critical oversight. We find that while participants in the structural mental model condition demonstrate a better understanding of the system, this can have a backfiring effect: while these participants judged the system as more usable, they also produced letters with more grammatical errors, highlighting a complex relationship between system understanding, trust, and control in contexts that require user oversight of error-prone AI outputs.2026SRShalaleh Rismani et al.McGill UniversityHuman-LLM CollaborationExplainable AI (XAI)AI-Assisted Writing & Text GenerationCHI
What If Moderation Didn’t Mean Suppression? A Case for Personalized Content TransformationCentralized content moderation paradigm both falls short and overreaches: 1) it fails to account for the subjective nature of harm, and 2) it acts with blunt suppression in response to content deemed harmful, even when such content can be salvaged. We first investigate this through formative interviews, documenting how seemingly benign content becomes harmful due to individual life experiences. Based on these insights, we developed DIY-MOD, a browser extension that operationalizes a new paradigm: personalized content transformation. Operating on a user's own definition of harm, DIY-MOD transforms sensitive elements within content in real-time instead of suppressing the content itself. The system selects the most appropriate transformation for a piece of content from a diverse palette---from obfuscation to artistic stylizing---to match the user's specific needs while preserving the content's informational value. Our two user studies demonstrate that this approach increases users' sense of agency and safety, enabling them to engage with content and communities they previously needed to avoid.2026RRRayhan Rashed et al.University of MichiganDark Patterns RecognitionSocial Platform Design & User BehaviorParticipatory DesignCHI
Instructional Mechanisms for Professional Writing: A Comparison of Scaffolded Annotation and ChatGPTProfessional writing skills are essential for crafting job application materials where applicants showcase their qualifications to recruiters and employers. Lettersmith is a digital tool that supports writing through scaffolded annotation, an instructional approach combining an expert-informed checklist, annotated examples, and self-tagging. We evaluated the efficacy of the instructional mechanisms that make up scaffolded annotation, as well as the use of ChatGPT, in facilitating writing cognitive processes and writing quality. Through a lab experiment with 146 first-year college students writing and revising a cover letter, we found that the combined mechanisms of scaffolded annotation within Lettersmith promoted a stronger understanding of the writing genre. Specifically, the use of a checklist combined with another writing support, like an example or self-tagging, was particularly effective for improving writing quality. Unstructured use of ChatGPT did not improve writing cognitive processes or writing quality more than Lettersmith.2026SCShanley Corvite et al.University of MichiganCollaborative Writing ToolsAI-Assisted Writing & Text GenerationUser Research Methods (Interviews, Surveys, Observation)CHI
"I can take what I want and adapt as needed": BIPOC Identity Making and Resistance Through Internet Aesthetics on TikTokInternet Aesthetics are personal styles that are curated, instantiated, and remade on social media through collections of art, fashion, sensory experiences, literature, and media to communicate and share lifestyle narratives. BIPOC users often use Internet Aesthetics on TikTok as identity-making tools. However, they may experience algorithmic symbolic annihilation in which the platform neglects the existence of BIPOC in particular Internet Aesthetics, reducing their agency over their online identity-making. Using semi-structured interviews, we identify how BIPOC users understand Internet Aesthetics and what strategies BIPOC use to engage with them on TikTok. We discuss how BIPOC users apply algorithmic folk theories and offline strategies to resist symbolic annihilation while engaging in identity-making by extracting joy and meaning from Internet Aesthetics. We also model the uncertainty BIPOC users face around experiencing symbolic annihilation using the concept of microaggressions and give guidance on designing tools to addressing this phenomenon.2026NCNatalie Chen et al.University of MichiganGender & Race Issues in HCISocial Platform Design & User BehaviorAI Ethics, Fairness & AccountabilityCHI
The Engagement-Prolonging Designs Teens Encounter on Very Large Online PlatformsIn the attention economy, online platforms are incentivized to design products that maximize user engagement, even when such practices conflict with users' best interests. We conducted a structured content analysis of all Very Large Online Platforms (VLOPs) to identify the designs these influential apps and sites use to capture attention and extend engagement. Specifically, we conducted this analysis posing as a teenager to identify the designs that young people are exposed to. We find that VLOPs use four strategies to extend teens' use: pressuring, enticing, trapping, and lulling them into spending more time online. We report on a hierarchical taxonomy organizing the 63 designs that fall under these categories. Applying this taxonomy to all 17 VLOPs, we identify 583 instances of engagement-prolonging designs, with social media platforms using twice as many as other VLOPs. We present three vignettes illustrating how these designs reinforce one another in practice. We further contribute a graphical dataset of videos illustrating these features in the wild.2026YCYixin Chen et al.University of WashingtonDark Patterns RecognitionCyberbullying & Online HarassmentYouth Online Safety & PrivacyCHI
Toward Scalable and Responsible Integration of Course-Specific AI Tutors: Instructor Experiences with a Campus-Wide Platform Despite rapid investment in generative AI across higher education, how instructors create, evaluate, and implement course-specific AI tutors remain empirically underexplored, highlighting critical tensions between institutional adoption and instructional practices. Drawing on interviews with 20 instructors, teaching assistants, and instructional designers at a large U.S. research university, we examine how participants engaged with a university-wide platform for creating course-specific AI tutors. Our findings reveal how instructors’ epistemic beliefs and pedagogical orientations shaped their perceptions of appropriate and inappropriate AI uses, as well as how instructional challenges motivated tutor creation across disciplines, class sizes, and course levels. We also identified three key patterns in instructor evaluation of course-specific AI tutors, along with the pedagogical, technical, and ethical implementation challenges they faced. We contribute timely insights to inform research, platform development, and institutional policy toward the responsible and scalable integration of course-specific AI tutors in higher education.2026EKEunhye Grace Ko et al.University of Texas at AustinHuman-LLM CollaborationAI-Assisted Decision-Making & AutomationAI Ethics, Fairness & AccountabilityCHI
Patchworking Networks of Support: On the Digital Successes and Challenges of Women- and Minority-Owned Restaurant BusinessesThe restaurant industry has become increasingly reliant on digital technologies for business operations, digital marketing, and promotion, especially amid and after the Covid-19 pandemic. This paper presents the findings of a two-year study exploring how women- and minority-owned restaurants in Chicago and Detroit encountered and overcame digital challenges in their day-to-day operations, across a range of levels of digital skills and literacy. Drawing from semi-structured and impromptu interviews with restaurant owners (n=47) and participant observation, we apply HCI literature on infrastructuring and patchworking to highlight how restaurateurs' experiences often run counter to the assumptions of a "typical" user. Indeed, they often must build and leverage their—offline and online—networks of support to overcome failing infrastructures, both within the restaurant industry and on digital platforms. Concurrently, we emphasize the importance of community building and social infrastructuring to overcome these challenges while also building up alternative networks of resources for their communities, especially considering identity-related inequalities and amid a global moment of crisis.2026MBMatthew Bui et al.University of MichiganDeveloping Countries & HCI for Development (HCI4D)Inclusive DesignCommunity Engagement & Civic TechnologyCHI