PAPERS
What Do We Mean When We Talk about Trust in Social Media? A Systematic Review
Yixuan Zhang, Joseph Gaggiano, Nutchanon Yongsatianchot, Nurul Suhaimi, Miso Kim, Yifan Sun, Jacqueline Griffin, Andrea Parker
Do people trust social media? If so, why, in what contexts, and how does that trust impact their lives? Researchers, companies, and journalists alike have increasingly investigated these questions, which are fundamental to understanding social media interactions and their implications for society. However, trust in social media is a complex concept, and there is conflicting evidence about the antecedents and implications of trusting social media content, users, and platforms. More problematic is that we lack basic agreement as to what trust means in the context of social media. Addressing these challenges, we conducted a systematic review to identify themes and challenges in this field. Through our analysis of 70 papers, we contribute a synthesis of how trust in social media is defined, conceptualized, and measured, a summary of trust antecedents in social media, an understanding of how trust in social media impacts behaviors and attitudes, and directions for future work.
Tingyu Cheng, Taylor Tabb, Jung Wook Park, Eric Gallo, Aditi Maheshwari, Gregory Abowd, HyunJoo Oh, Andreea Danielescu
Today’s electronics are manufactured to provide stable functionality and fixed physical forms optimized for reliable operation over long periods and repeated use. However, even when applications don’t call for such robustness, the permanency of these electronics comes with environmental consequences. In this paper, we describe an alternative approach that utilizes sustainable transient electronics whose method of destruction is also key to their functionality. We create these electronics through three different methods: 1) by inkjet printing conductive silver traces on poly(vinyl alcohol) (PVA) substrates to create water-soluble sensors; 2) by mixing a conductive beeswax material configured as a meltable sensor; and 3) by fabricating edible electronics with 3D printed chocolate and culinary gold leaf. To enable practical applications of these devices, we implement a fully transient and sustainable chipless RF detection system.
Jiawei Zhou, Yixuan Zhang, Qianni Luo, Andrea Parker, Munmun De Choudhury
Large language models have abilities in creating high-volume human-like texts and can be used to generate persuasive misinformation. However, the risks remain under-explored. To address the gap, this work first examined characteristics of AI-generated misinformation (AI-misinfo) compared with human creations, and then evaluated the applicability of existing solutions. We compiled human-created COVID-19 misinformation and abstracted it into narrative prompts for a language model to output AI-misinfo. We found significant linguistic differences within human-AI pairs, and patterns of AI-misinfo in enhancing details, communicating uncertainties, drawing conclusions, and simulating personal tones. While existing models remained capable of classifying AI-misinfo, a significant performance drop compared to human-misinfo was observed. Results suggested that existing information assessment guidelines had questionable applicability, as AI-misinfo tended to meet criteria in evidence credibility, source transparency, and limitation acknowledgment. We discuss implications for practitioners, researchers, and journalists, as AI can create new challenges to the societal problem of misinformation.
Darley Sackitey, Teresa O’Leary, Michael Paasche-Orlow, Timothy Bickmore, Andrea Parker
Faith institutions provide social support and community care for many in the United States (U.S.). Notably, churches with predominantly Black populations have served as a site for social change and care provision, historically and in contemporary society. However, the pandemic has emphasised how localising these care networks in physical spaces can limit access to social support. Information and communication technologies offer opportunities for expanding access to care in these communities. However, integrating care networks into online contexts remains a challenge for many churches, and the potential for technology to expand these networks is not well understood. Through interviews and focus groups with nine church members, we explore how hybrid faith communities that bridge offline and online contexts can enable social support and care provision. Our findings highlight care network structures in Black churches, barriers to embedding these networks online and strategies for building more seamless hybrid support systems.
Anupriya Tuli, Azra Ismail, Karthik S Bhat, Pushpendra Singh, Neha Kumar
There has been a growing interest in reproductive health and intimate wellbeing in Human-Computer Interaction, increasingly from an ecological perspective. Much of this work is centered around women’s experiences across diverse settings, emphasizing men’s limited engagement and need for greater participation on these topics. Our research responds to this gap by investigating cisgender men’s experiences of cultivating sexual health literacies in an urban Indian context. We leverage media probes to stimulate focus group discussions, using popular media references on men’s fertility to elicit shared reflection. Our findings uncover the role that humor and masculinity play in shaping men’s perceptions of their sexual health and how this influences their sense of agency and participation in heterosexual intimate relationships. We further discuss how technologies might be designed to support men’s participation in these relationships as supportive partners and allies.
“Moment to Moment”: A View From the Front Lines with Computing Ethics Teaching Assistants
Cass Zegura, Ben Shapiro, Robert MacDonald, Jason Borenstein, Ellen Zegura
The HCI research community has long centered ethics in HCI research and practice. This interest has persisted as scholars highlight the need for more situated understandings and deeper integration of ethics into HCI. In parallel, HCI scholars and students have become increasingly involved in teaching computing ethics across many different university contexts, bringing in valuable perspectives informed by the connections between HCI and the socio-technical subject matter of computing ethics. Yet explicitly bringing these two threads together – examining the teaching of ethics through an HCI research lens – remains nascent. This paper integrates work in HCI and computing education to focus on the role and experience of computing ethics teaching assistants (CETAs), who are increasingly involved in ethics instruction and whose perspectives are predominantly missing in existing literature spanning HCI and computing education. Drawing on HCI theories and methods, our qualitative study of eleven CETAs at two American universities makes three contributions to the HCI literature. First, we build an understanding of who these TAs are with respect to the unique position of teaching computing ethics. Second, we characterize how CETAs’ teaching and learning is situated and shaped within different communities and institutional contexts. Finally, we sug- gest several implications for the design of ethics instruction within undergraduate computing programs. More broadly, our work can be viewed as a call to action, encouraging HCI scholars to play a more significant role in studying and designing the teaching and learning of computing ethics.
Accidentally Evil: On Questionable Values in Smart Home Co-Design
Arne Berger, Albrecht Kurze, Andreas Bischof, Jesse Benjamin, Richmond Wong, Nick Merrill
An ongoing mystery of HCI is how do well-intentioned designers consistently enable products with unintentionally evil consequences. Using “questionable values” as a lens, we retell and analyze four design scenarios for smart homes that were created by participants with an IoT toolkit we designed. The selected design scenarios reveal practices that violate principles of responsible smart home design. Through our analysis we show (1) how participants explore sensor-driven objectification of the home then leverage data for surveillance, nudging, and control over others; (2) how the dominant technosolutionist narratives of efficiency and productivity ground such questionable values; (3) and how the materiality of mass-produced sensors pre-mediates questionable design scenarios. We discuss how to attend to and utilize questionable values in design: Making space for questionable values will empower design researchers to better “look around corners”, anticipating tomorrow’s concerns and forestalling the worst of their harms.
Vedant Das Swain, Lan Gao, William Wood, Srikruthi C Matli, Gregory Abowd, Munmun De Choudhury
We are witnessing an emergence in Passive Sensing enabled AI (PSAI) to provide dynamic insights for performance and wellbeing of information workers. Hybrid work paradigms have simultaneously created new opportunities for PSAI, but have also fostered anxieties of misuse and privacy intrusions within a power asymmetry. At this juncture, it is unclear if those who are sensed can find these systems acceptable. We conducted scenario-based interviews of 28 information workers to highlight their perspectives as data subjects in PSAI. We unpack their expectations using the Contextual Integrity framework of privacy and information gathering. Participants described appropriateness of PSAI based on its impact on job consequences, work-life boundaries, and preservation of flexibility. They perceived that PSAI inferences could be shared with selected stakeholders if they could negotiate the algorithmic inferences. Our findings help envision worker-centric approaches to implementing PSAI as an empowering tool in the future of work.
Vanessa Oguamanam, Natalie Hernandez, Rasheeta Chandler, Dominique Guillaume, Kai McKeever, Morgan Allen, Sabreen Mohammed, Andrea Parker
In the United States (U.S.), Black women in the perinatal period disproportionately experience higher rates of mental health challenges like anxiety and postpartum depression. Digital platforms present promising opportunities for mental health support. However, the extent to which these tools are being adopted and satisfying the mental health needs amongst perinatal Black women is underexplored. To address this gap, we surveyed 101 pregnant and postpartum Black women in the U.S. Despite prior work showing low utilization of mental health services amongst Black women, our results show more than half of our participants using specific digital tools for mental health support (e.g., mobile apps and social media). Importantly, use and satisfaction with these tools varied by subgroups (e.g., income and education level). We use our findings to present recommendations for digital mental health intervention research that incorporates an understanding of intersectional identities during the perinatal period.
Angler: Helping Machine Translation Practitioners Prioritize Model Improvements
Samantha Robertson, Zijie Wang, Dominik Moritz, Mary Beth Kery, Fred Hohman
Machine learning (ML) models can fail in unexpected ways in the real world, but not all model failures are equal. With finite time and resources, ML practitioners are forced to prioritize their model debugging and improvement efforts. Through interviews with 13 ML practitioners at Apple, we found that practitioners construct small targeted test sets to estimate an error’s nature, scope, and impact on users. We built on this insight in a case study with machine translation models, and developed Angler, an interactive visual analytics tool to help practitioners prioritize model improvements. In a user study with 7 machine translation experts, we used Angler to understand prioritization practices when the input space is infinite, and obtaining reliable signals of model quality is expensive. Our study revealed that participants could form more interesting and user-focused hypotheses for prioritization by analyzing quantitative summary statistics and qualitatively assessing data by reading sentences.
Causalvis: Visualizations for Causal Inference
Grace Guo, Ehud Karavani, Alex Endert, Bum Chul Kwon
Causal inference is a statistical paradigm for quantifying causal effects using observational data. It is a complex process, requiring multiple steps, iterations, and collaborations with domain experts. Analysts often rely on visualizations to evaluate the accuracy of each step. However, existing visualization toolkits are not designed to support the entire causal inference process within computational environments familiar to analysts. In this paper, we address this gap with Causalvis, a Python visualization package for causal inference. Working closely with causal inference experts, we adopted an iterative design process to develop four interactive visualization modules to support causal inference analysis tasks. The modules are then presented back to the experts for feedback and evaluation. We found that Causalvis effectively supported the iterative causal inference process. We discuss the implications of our findings for designing visualizations for causal inference, particularly for tasks of communication and collaboration.
Data Practice for a Politics of Care: Food Assistance as a Site of Careful Data Work
Ashley Boone, Carl DiSalvo, Christopher Le Dantec
As data plays an increasing role in civic decision making, diverse organizations are facing pressure to engage in data work. The HCI community has explored both the potential of and challenges to integrating robust data practices in mission-driven organizations. At each step – from collection, to storage, to analysis, to maintenance – these organizations need to develop tools and practices that balance internal operational needs and external community priorities. This work reports on an 11 month-long collaboration with a mission-driven hybrid organization that has designed tools and procedures for collecting data that enact an ethic of care. This caring data practice is characterized by defining success through relationships, attending to the social and cultural community context, and protecting vulnerable populations through non-collection. We share the organization’s practices, analyze how they support the organization in providing care, and offer recommendations for building caring data systems.
Arpit Narechania, Fan Du, Atanu Sinha, Ryan Rossi, Jane Hoffswell, Shunan Guo, Eunyee Koh, Shamkant Navathe, Alex Endert
Selecting relevant data subsets from large, unfamiliar datasets can be difficult. We address this challenge by modeling and visualizing two kinds of auxiliary information: (1) quality – the validity and appropriateness of data required to perform certain analytical tasks; and (2) usage – the historical utilization characteristics of data across multiple users. Through a design study with 14 data workers, we integrate this information into a visual data preparation and analysis tool, DataPilot. DataPilot presents visual cues about “the good, the bad, and the ugly” aspects of data and provides graphical user interface controls as interaction affordances, guiding users to perform subset selection. Through a study with 36 participants, we investigate how DataPilot helps users navigate a large, unfamiliar tabular dataset, prepare a relevant subset, and build a visualization dashboard. We find that users selected smaller, effective subsets with higher quality and usage, and with greater success and confidence.
Designing Responsible AI: Adaptations of UX Practice to Meet Responsible AI Challenges
Qiaosi Wang, Michael Madaio, Shaun Kane, Shivani Kapania, Michael Terry, Lauren Wilcox
“Technology companies continue to invest in efforts to incorporate responsibility in their Artificial Intelligence (AI) advancements, while efforts to audit and regulate AI systems expand. This shift towards Responsible AI (RAI) in the tech industry necessitates new practices and adaptations to roles—undertaken by a variety of practitioners in more or less formal positions, many of whom focus on the user-centered aspects of AI. To better understand practices at the intersection of user experience (UX) and RAI, we conducted an interview study with industrial UX practitioners and RAI subject matter experts, both of whom are actively involved in addressing RAI concerns throughout the early design and development of new AI-based prototypes, demos, and products, at a large technology company. Many of the specifc practices and their associated challenges have yet to be surfaced in the literature, and distilling them offers a critical view into how practitioners’ roles are adapting to meet present-day RAI challenges. We present and discuss three emerging practices in which RAI is being enacted and reifed in UX practitioners’ everyday work. We conclude by arguing that the emerging practices, goals, and types of expertise that surfaced in our study point to an evolution in praxis, with associated challenges that suggest important areas for further research in HCI.”
EquityWare: Co-Designing Wearables With And For Low Income Communities In The U.S.
Stefany Cruz, Alexander Redding, Connie Chau, Claire Lu, Julia Persche, Josiah Hester, Maia Jacobs
Wearables are a potentially vital mechanism for individuals to monitor their health, track behaviors, and stay connected. Unfortunately, both price and a lack of consideration of the needs of low-SES communities have made these devices inaccessible and unusable for communities that would most substantially benefit from their affordances. To address this gap and better understand how members of low-SES communities perceive the potential benefits and barriers to using wearable devices, we conducted 19 semi-structured interviews with people from minority, high crime rate, low-SES communities. Participants emphasized a critical need for safety-related wearable devices in their communities. Still, existing tools do not yet address the specific needs of this community and are out of reach due to several barriers. We distill themes on perceived useful features and ongoing obstacles to guide a much-needed research agenda we term ‘Equityware’: building wearable devices based on low-SES communities’ needs, comfortability, and limitations.
Focused Time Saves Nine: Evaluating Computer-Assisted Protected Time for Hybrid Information Work
Vedant Das Swain, Javier Hernandez, Brian Houck, Koustuv Saha, Jina Suh, Ahad Chaudhry, Tenny Cho, Wendy Guo, Shamsi Iqbal, Mary Czerwinski
Information workers often struggle to balance their time for a variety of activities like focused work, communication, and caring. This study analyzes the impact of a commercially available computer-assisted time protection intervention that automatically and preemptively schedules calendar time for self-determined activities. We analyzed the behaviors and self-reports of workers in two naturalistic studies. First, we studied 27 workers who were already using Computer-Assisted Protected Time (CAP Time) and found that they mainly used it for focused work. Second, we analyzed the effect of CAP Time as a randomized intervention on 89 workers who never had CAP Time and found that those with it self-reported an increase in performance, job resources, and immersion. In both studies, workers with CAP Time exhibited a rearrangement of activities leading to an overall reduction in work activity. This study highlights new opportunities for intelligent time-management interventions and the importance of protected time at work.
GAM Coach: Towards Interactive and User-centered Algorithmic Recourse
Zijie Wang, Jennifer Wortman Vaughan, Rich Caruana, Duen Horng Chau
Machine learning (ML) recourse techniques are increasingly used in high-stakes domains, providing end users with actions to alter ML predictions, but they assume ML developers understand what input variables can be changed. However, a recourse plan’s actionability is subjective and unlikely to match developers’ expectations completely. We present GAM Coach, a novel open-source system that adapts integer linear programming to generate customizable counterfactual explanations for Generalized Additive Models (GAMs), and leverages interactive visualizations to enable end users to iteratively generate recourse plans meeting their needs. A quantitative user study with 41 participants shows our tool is usable and useful, and users prefer personalized recourse plans over generic plans. Through a log analysis, we explore how users discover satisfactory recourse plans, and provide empirical evidence that transparency can lead to more opportunities for everyday users to discover counterintuitive patterns in ML models. GAM Coach is available at: https://poloclub.github.io/gam-coach/.
It Takes (at least) Two: The Work to Make Romance Work
Vishal Sharma, Kirsten Bray, Neha Kumar, Rebecca E. Grinter
Digitalization has motivated romance novelists to move from traditional to self-publishing online. However, engagement with flexible and responsive, yet precarious and biased algorithmic systems online pose challenges for novelists. Through surveying and interviewing the novelists, and using the lens of feminist political economy, we investigate how digitalization has impacted the novelists’ work practices. Our findings detail the increased agency afforded by self-publishing online, which comes at the expense of performing new forms of work individually, collectively, and with assistance, otherwise performed by publishing houses. We focus on the immaterial, invisible, and unpaid work that the novelists and the ecology of workers surrounding them conducted. We make recommendations for designing digital labor platforms that support the work practices of self-employed digital workers toward a more sustainable, collective, and inclusive future(s) of work.
Learning to Navigate Health Taboos through Online Safe Spaces
Hannah Tam, Karthik S Bhat, Priyanka Mohindra, Neha Kumar
Social and cultural taboos frequently prevent meaningful conversation around gendered health and wellbeing, across the globe and to varying degrees. Safe spaces can offer potential avenues to nurture non-judgmental environments for dialogue and opportunities for learning to talk through taboos. To this end, we curated an online safe space on WhatsApp—with 35 participants of Indian origin—to facilitate conversations around diverse topics related to gendered health and wellbeing. We observed participant activity for two weeks, before conducting in-depth interviews with 10 participants to better understand their experiences of engaging within the WhatsApp group. We use the lens of Legitimate Peripheral Participation to examine how peripheral and core members of the community drew on new audiences and support systems as they questioned existing structures upholding taboos. We discuss scaffolding mechanisms that could enhance learning about taboo topics in online safe spaces, and the tensions of anonymity in such learning spaces.
Metrics for Peer Counseling: Triangulating Success Outcomes for Online Therapy Platforms
Tony Wang, Haard Shah, Raj Shah, Yi-Chia Wang, Robert Kraut, Diyi Yang
Extensive research has been published on the conversational factors of effective volunteer peer counseling on online mental health platforms (OMHPs). However, studies differ in how they define and measure success outcomes, with most prior work examining only a single success metric. In this work, we model the relationship between previously reported linguistic predictors of effective counseling with four outcomes following a peer-to-peer session on a single OMHP: retention in the community, following up on a previous session with a counselor, users’ evaluation of a counselor, and changes in users’ mood. Results show that predictors correlate negatively with community retention but positively with users following up with and giving higher evaluations to individual counselors. We suggest actionable insights for therapy platform design and outcome measurement based on findings that the relationship between predictors and outcomes of successful conversations depends on differences in measurement construct and operationalization.
Mobilizing Social Media Data: Reflections of a Researcher Mediating between Data and Organization
Adriana Alvarado Garcia, Marisol Wong-Villacres, Milagros Miceli, Benjamín Hernández, Christopher Le Dantec
This paper examines the practices involved in mobilizing social media data from their site of production to the institutional context of non-profit organizations. We report on nine months of fieldwork with a transnational and intergovernmental organization using social media data to understand the role of grassroots initiatives in Mexico, in the unique context of the COVID-19 pandemic. We show how different stakeholders negotiate the definition of problems to be addressed with social media data, the collective creation of ground-truth, and the limitations involved in the process of extracting value from data. The meanings of social media data are not defined in advance; instead, they are contingent on the practices and needs of the organization that seeks to extract insights from the analysis. We conclude with a list of reflections and questions for researchers who mediate in the mobilization of social media data into non-profit organizations to inform humanitarian action.
Shravika Mittal, Munmun De Choudhury
Mental health discussions on public forums influence the perceptions of people. Negative consequences may result from hostile and “othering” portrayals of people with mental disorders. Adopting the lens of Moral Foundation Theory (MFT), we study framings of mental health discourse on Twitter and News, and how moral underpinnings abate or exacerbate stigma. We adopted a large language model based representation framework to score 13,277,115 public tweets and 21,167 news articles against MFT’s five foundations. We found discussions on Twitter to demonstrate compassion, justice and equity-centered moral values for those suffering from mental illness, in contrast to those on News. That said, stigmatized discussions appeared on both Twitter and News, with news articles being more stigmatizing than tweets. We discuss implications for public health authorities to refine measures for safe reporting of mental health, and for social media platforms to design affordances that enable empathetic discourse.
Slide Gestalt: Automatic Structure Extraction in Slide Decks for Non-Visual Access
Yi-Hao Peng, Peggy Chi, Anjuli Kannan, Meredith Morris, Irfan Essa
Presentation slides commonly use visual patterns for structural navigation, such as titles, dividers, and build slides. However, screen readers do not capture such intention, making it time-consuming and less accessible for blind and visually impaired (BVI) users to linearly consume slides with repeated content. We present Slide Gestalt, an automatic approach that identifies the hierarchical structure in a slide deck. Slide Gestalt computes the visual and textual correspondences between slides to generate hierarchical groupings. Readers can navigate the slide deck from the higher-level section overview to the lower-level description of a slide group or individual elements interactively with our UI. We derived side consumption and authoring practices from interviews with BVI readers and sighted creators and an analysis of 100 decks. We performed our pipeline with 50 real-world slide decks and a large dataset. Feedback from eight BVI participants showed that Slide Gestalt helped navigate a slide deck by anchoring content more efficiently, compared to using accessible slides.
Adrian Choi, Catherine D’Ignazio, Brooke Foucault Welles, Andrea Parker
Social injustices are commonly discussed on social media, presenting opportunities for youth to engage with this content and develop into engaged citizens. While much has been written about youths’ online activism, less is known about how engaging with sociopolitical content may build their capacity for activist work. We explore the extent to which youths’ engagement with sociopolitical content on various social media platforms is associated with critical consciousness—an awareness of inequities, the motivation to address them, and action that combats injustice. To investigate this relationship, we conducted a survey with 339 high school-aged youths. While sociopolitical engagement on some platforms was positively associated with youths’ critical consciousness measures, sociopolitical engagement on other platforms was negatively associated. Qualitative post-hoc analysis was used to suggest reasons for possible differences. In light of our findings, we discuss the relationship between online sociopolitical engagement and critical consciousness and suggest directions for future work.
SwellSense: Creating 2.5D interactions with micro-capsule paper
Tingyu Cheng, Zhihan Zhang, Bingrui Zong, Yuhui Zhao, Zekun Chang, Ye Jun Kim, Clement Zheng, Gregory Abowd, HyunJoo Oh
In this paper, we propose SwellSense, a fabrication technique to screen print stretchable circuits onto a special micro-capsule paper, creating localized swelling patterns with sensing capabilities. This simple technique will allow users to create a wide range of paper-based tactile interactive devices, which are mostly maintaining 2D planar form factor but can also be curved or folded into 3D interactive artifacts. We first present the design guidelines to support various tactile interaction design including basic tactile graphic geometries, patterns with directional density, or finer interactive textures with embedded sensing such as touch sensor, pressure sensor, and mechanical switch. We then provide a design editor to enable users to design more creatively using the SwellSense technique. We provide a technical evaluation and user evaluation to validate the basic performance of SwellSense. Lastly, we demonstrate several application examples and conclude with a discussion on current limitations and future work.
Rachel Lowy, Lan Gao, Kaely Hall, Jennifer Kim
Inclusive workplaces require mutual efforts between neurotypical (NT) and neurodivergent (ND) employees to understand one another’s viewpoints and experiences. Currently, the majority of inclusivity training places the burden of change on NDs to conform to NT social-behavioral standards. Our research examines moving toward a more equal effort distribution by exploring virtual reality (VR) design opportunities to build NTs’ understanding of ND workplace experiences. Using participatory design, including generative toolkits and design meetings, we surfaced two main themes that could bridge gaps in understanding: (1) NTs’ recognition of NDs’ strengths and efforts at work, and (2) NTs’ understanding of NDs’ differences. We present a strengths-based assessment of ND traits in the workplace, focusing on how workplaces can support NDs’ success. Finally, we propose VR simulation designs that communicate these themes to represent ND experiences, emphasizing their strengths and viewpoints so that NT co-workers can better empathize and accommodate them.
Towards Intermediated Workflows for Hybrid Telemedicine
Karthik S Bhat, Neha Kumar, Karthik Shamanna, Nipun Kwatra, Mohit Jain
The growing platformization of health has spurred new avenues for healthcare access and reinvigorated telemedicine as a viable pathway to care. Telemedicine adoption during the COVID-19 pandemic has surfaced barriers to patient-centered care that call for attention. Our work extends current Human-Computer Interaction (HCI) research on telemedicine and the challenges to remote care, and investigates the scope for enhancing remote care seeking and provision through telemedicine workflows involving intermediation. Our study, focused on the urban Indian context, involved providing doctors with videos of remote clinical examinations to aid in telemedicine. We present a qualitative evaluation of this modified telemedicine experience, highlighting how workflows involving intermediation could bridge existing gaps in telemedicine, and how their acceptance among doctors could shift interaction dynamics between doctors and patients. We conclude by discussing the implications of such telemedicine workflows on patient-centered care and the future of care work.
Translation as (Re)mediation: How Ethnic Community-Based Organizations Negotiate Legitimacy
Cella Sum, Anh-Ton Tran, Jessica Lin, Rachel Kuo, Cynthia Bennett, Christina Harrington, Sarah Fox
Ethnic community-based organizations (CBOs) play an essential role in supporting the wellbeing of immigrants and refugees. CBO workers often act as linguistic and cultural translators between communities, government, and health and social service systems. However, resource constraints, technological barriers, and pressures to be data-driven require workers to perform additional forms of translation to ensure their organizations’ survival. Drawing on 16 interviews with members of 7 Asian American and Pacific Islander CBOs, we examine opportunities and barriers concerning their technology-mediated work practices. We identify two circumstances where CBO workers perform translation: (1) as legitimacy work to build trust with funders and communities, and (2) as (re)mediation in attending to technological barriers and resisting hegemonic systems that treat their communities as “other.” By unpacking the politics of translation work across these sites, we position CBO workers as a critical source for HCI research and practice as it seeks to support community wellbeing.
Why Johnny Can’t Prompt: How Non-AI Experts Try (and Fail) to Design LLM Prompts
J.D. Zamfirescu-Pereira, Richmond Wong, Bjoern Hartmann, Qian Yang
Pre-trained large language models (“LLMs”) like GPT-3 can engage in fluent, multi-turn instruction-taking out-of-the-box, making them attractive materials for designing natural language interactions. Using natural language to steer LLM outputs (“prompting”) has emerged as an important design technique potentially accessible to non-AI-experts. Crafting effective prompts can be challenging, however, and prompt-based interactions are brittle. Here, we explore whether non-AI-experts can successfully engage in “end-user prompt engineering” using a design probe—a prototype LLM-based chatbot design tool supporting development and systematic evaluation of prompting strategies. Ultimately, our probe participants explored prompt designs opportunistically, not systematically, and struggled in ways echoing end-user programming systems and interactive machine learning systems. Expectations stemming from human-to-human instructional experiences, and a tendency to overgeneralize, were barriers to effective prompt design. These findings have implications for non-AI-expert-facing LLM-based tool design and for improving LLM-and-prompt literacy among programmers and the public, and present opportunities for further research.
LATE-BREAKING WORK
Experts Prefer Text but Videos Help Novices: An Analysis of the Utility of Multi-Media Content
Hayeong Song, Alexa Siu, Curtis Wigington, Jennifer Healey, John Stasko
Multi-media increases engagement and is increasingly prevalent in online content including news, web blogs, and social media, however, it may not always be beneficial to users. To determine what types of media users actually wanted, we conducted an exploratory study where users got to choose their own media augmentation. Our findings showed that readers desired different amounts and types of media depending on their familiarity with the content. To further investigate this difference, we created two versions of a media augmented document, one designed for novices and one designed for experts. We evaluated these prototypes in a two-way between subject study with 48 participants and found that while multi-media enhanced novice readers’ perception of usability (p = .0100) and helped them with reading time (p = .0427), time on task (p= .0156), comprehension (p = .0161), experts largely ignored multi-media and primarily utilized text.
Junyu Chen, Xiongqi Wang, Juling Li, George Chernyshov, Yifei Huang, Kai Kunze, Jing Huang, Thad Starner, Qing Zhang
“Imbalanced food intake contributes to various diseases, such as obesity, diabetes, high blood pressure, high cholesterol, heart disease, and type-2 diabetes. At the same time, food intake monitoring systems play a significant role in the treatment.
Most current food intake tracking methods are camera-based, on-body sensor-based, microphone based, and self-reported. The challenges that remain are social acceptance, lightweight, easy to use, and inexpensive. Our method leverages two 6-axe Inertial Measurement Units (IMU) on the glasses’ leg and the wrist to detect the user’s food intake activities using a machine learning capable Micro Controller Unit (MCU).
We introduced the concept of the first bite/chew, which is a stable and reliable indicator to distinguish food types. Our implementation results show that our method can distinguish seven kinds of food at an accuracy of 93.26\% (average) over all four participants.”
Making Smart Cities Explainable: What XAI Can Learn from the “Ghost Map”
Shubhangi Gupta, Yanni Loukissas
How are cities represented in geospatial algorithms that guide the contemporary “smart city” life? Such representations do not passively describe cities; they actively guide city life. Algorithmic harms, such as gentrification, present an urgent need to open up these opaque systems for critique by city inhabitants. Explainable AI (XAI) approaches presented at CHI, while influential, are limited in their accessibility, cultural reflexivity, situatedness, and design visibility. In this paper, we argue that conventional maps, a common visualization technique for representing cities, hold useful lessons for addressing these gaps. Effective maps provide what we call ‘grounded explanations’. As a salient example, we use the historical ‘Ghost Map’ designed by John Snow to trace the 1854 London cholera epidemic. We hope this example can encourage the XAI community to learn from the cultural history of city representations as they seek to establish public processes for explaining and evaluating the “smart city” algorithms.
MultiViz: Towards User-Centric Visualizations and Interpretations of Multimodal Models
Paul Pu Liang, Yiwei Lyu, Gunjan Chhablani, Nihal Jain, Zihao Deng, Xingbo Wang, Louis-philippe Morency, Ruslan Salakhutdinov
The promise of multimodal models for real-world applications has inspired research in visualizing and understanding their internal mechanics with the end goal of empowering stakeholders to visualize model behavior, perform model debugging, and promote trust in machine learning models. However, modern multimodal models are typically black-box neural networks, which makes it challenging to understand their internal mechanics. How can we visualize the internal modeling of multimodal interactions in these models? Our paper proposes MultiViz, a method for analyzing the behavior of multimodal models via 4 stages: (1) unimodal importance, (2) cross-modal interactions, (3) multimodal representations and (4) multimodal prediction. Through studies with 21 users on 8 trained models across 6 real-world tasks, we show that the complementary stages in MultiViz together enable users to (1) simulate model predictions, (2) assign interpretable concepts to features, (3) perform error analysis on misclassifications, and (4) use insights from error analysis to debug models.
Workplace Rhythm Variability and Emotional Distress in Information Workers
Subigya Nepal, Javier Hernandez, Judith Amores Fernandez, Mehrab Bin Morshed, Robert Lewis, Hemma Prafullchandra, Mary Czerwinski
Regularity in daily activities has been linked to positive well-being outcomes, but previous studies have mostly focused on clinical populations and traditional daily activities such as sleep and exercise. This research extends prior work by examining the regularity of both self-reported and digital activities of 49 information workers in a 4-week naturalistic study. The data was analyzed in conjunction with self-reported stress, anxiety, and depression scores. The findings suggest that greater variability in self-reported mood, job demands, lunch time, and sleep quality may be associated with increased stress, anxiety, and depression. However, for digital activity-based measures, we find that the opposite is true—greater variability in digital rhythm is related with reduced emotional distress. This study expands our understanding of workers and the potential insights that can be gained from analyzing technology interactions and well-being.
WORKSHOPS & SYMPOSIA
AI Literacy: Finding Common Threads between Education, Design, Policy, and Explainability
Duri Long, Jessica Roberts, Brian Magerko, Kenneth Holstein, Daniella DiPaola, Fred Martin
Fostering public AI literacy has been a growing area of interest at CHI for several years, and a substantial community is forming around issues such as teaching children how to build and program AI systems, designing learning experiences to broaden public understanding of AI, developing explainable AI systems, understanding how novices make sense of AI, and exploring the relationship between public policy, ethics, and AI literacy. Previous workshops related to AI literacy have been held at other conferences (e.g., SIGCSE, AAAI) that have been mostly focused on bringing together researchers and educators interested in AI education in K-12 classroom environments, an important subfield of this area. Our workshop seeks to cast a wider net that encompasses both HCI research related to introducing AI in K-12 education and also HCI research that is concerned with issues of AI literacy more broadly, including adult education, interactions with AI in the workplace, understanding how users make sense of and learn about AI systems, research on developing explainable AI (XAI) for non-expert users, and public policy issues related to AI literacy.
Beyond prototyping boards: future paradigms for electronics toolkits
Andrea Bianchi, Steve Hodges, David Cuartielles, HyunJoo Oh, Mannu Lambrichts, Anne Roudaut
Electronics prototyping platforms such as Arduino enable a wide variety of creators with and without an engineering background to rapidly and inexpensively create interactive prototypes. By opening up the process of prototyping to more creators, and by making it cheaper and quicker, prototyping platforms and toolkits have undoubtedly shaped the HCI community. With this workshop, we aim to understand how recent trends in technology, from reprogrammable digital and analog arrays to printed electronics, and from metamaterials to neurally-inspired processors, might be leveraged in future prototyping platforms and toolkits. Our goal is to go beyond the well-established paradigm of mainstream microcontroller boards, leveraging the more diverse set of technologies that already exist but to date have remained relatively niche. What is the future of electronics prototyping toolkits? How will these tools fit in the current ecosystem? What are the new opportunities for research and commercialization?
Designing Technology and Policy Simultaneously: Towards A Research Agenda and New Practice
Qian Yang, Richmond Wong, Thomas Gilbert, Margaret Hagan, Steven Jackson, Sabine Junginger, John Zimmerman
HCI Across Borders: Towards Global Solidarity
Vikram Kamath Cannanure, Delvin Varghese, Cuauhtémoc Rivera-Loaiza, Faria Noor, Dipto Das, Pranjal Jain, Meiyin Chang, Marisol Wong-Villacres, Naveena Karusala, Nova Ahmed, Sarina Till, Bernard Akhigbe, Melissa Densmore, Susan Dray, Christian Sturm, Neha Kumar
Recent global developments, such as the war in Ukraine and uprisings in Iran, motivate this year’s HCI Across Borders (HCIxB) workshop at CHI 2023, asking how we can foster greater global solidarity. Our workshop aims to brainstorm and discuss pathways to engage in solidarity as a global research, practice, and education community. HCIxB has already gathered a diverse audience annually by conducting workshops and symposia annually since CHI 2016. At CHI 2023, we hope to hold a hybrid workshop to focus on themes of solidarity and resilience, and how we might support and nurture the growth of a diverse and growing body of students and early career researchers across the SIGCHI community.
Human-centered Explainable AI: Coming of Age
Upol Ehsan, Philipp Wintersberger, Elizabeth Watkins, Carina Manger, Gonzalo Ramos, Justin Weisz, Hal Daumé III, Andreas Riener, Mark Riedl
Explainability is an essential pillar of Responsible AI that calls for equitable and ethical Human-AI interaction. Explanations are essential to hold AI systems and their producers accountable, and can serve as a means to ensure humans’ right to understand and contest AI decisions. Human-centered XAI (HCXAI) argues that there is more to making AI explainable than algorithmic transparency. Explainability of AI is more than just “opening” the black box — who opens it matters just as much, if not more, as the ways of opening it. In this third CHI workshop on Human-centered XAI (HCXAI), we build on the maturation through the first two installments to craft the coming-of-age story of HCXAI, which embodies a deeper discourse around operationalizing human-centered perspectives in XAI. We aim towards actionable interventions that recognize both affordances and potential pitfalls of XAI. The goal of the third installment is to go beyond the black box and examine how human-centered perspectives in XAI can be operationalized at the conceptual, methodological, and technical levels. Encouraging holistic (historical, sociological, and technical) approaches, we emphasize “operationalizing.” Within our research agenda for XAI, we seek actionable analysis frameworks, concrete design guidelines, transferable evaluation methods, and principles for accountability
Integrating Individual and Social Contexts into Self-Reflection Technologies
Ananya Bhattacharjee, Dana Kulzhabayeva, Mohi Reza, Harsh Kumar, Eunchae Seong, Xuening Wu, Mohammad Rashidujjaman Rifat, Robert Bowman, Rachel Kornfield, Alex Mariakakis, Syed Ishtiaque Ahmed, Munmun De Choudhury, Gavin Doherty, Mary Czerwinski, Joseph Williams
Technology for promoting reflection can help people better understand their emotions and thought patterns, eventually motivating them to take action to adopt healthy or productive behaviors. However, existing work has often viewed users individualistically, addressing people’s behaviors and emotions rather than recognizing the external factors that shape them (e.g., economic status, culture). We envision that the individualistic approaches can be extended and reimagined in ways that can consider such broader contexts.We believe such a shift in the design of interventions will help individuals reflect in a more holistic manner, supporting collaborative reflection processes that involve more than one person. With these aims in mind, we will discuss the two questions in our workshop. First, what individual and social contexts should HCI researchers consider while promoting reflection? Second, what role can various forms of technology (e.g., just-in-time adaptive interventions, peer-support platforms) play in supporting and augmenting reflective practices? Through our workshop, we hope to bring together a community of multidisciplinary researchers and practitioners who aim to design and develop reflection interventions that are situated within the fabric of users’ individual and social contexts.
The Future of Hybrid Care and Wellbeing in HCI
Karthik S Bhat, Azra Ismail, Amanda Hall, Naveena Karusala, Helena M. Mentis, John Vines, Neha Kumar
MORE RESEARCH
Case Studies
Experience: Barriers and Opportunities of Wearables for Eating Research
Mahdi Pedram, Glenn Fernandes, Christopher Romano, Boyang Wei, Sougata Sen, Josiah Hester, Nabil Alshurafa
Wearable devices have long held the potential to provide real-time objective measures of behavior. However, due to challenges in real-world deployment, these systems are rarely tested rigorously in free-living settings. To reduce this challenge for future researchers, in this paper, we describe our experience developing several generations of a multi-sensor, neck-worn eating-detection system that has been tested with 130 participants across multiple studies in both laboratory and free-living settings. We describe the challenges faced in the development and deployment of the system by (1) presenting example deployment details captured either by the sensing system or the ground truth collector and (2) using structured interviews and surveys with developers and stakeholders of the system, collecting qualitative data on their experience. We performed thematic analysis and provided detailed lessons learned explaining factors that impact the experience of building and deploying such a wearable in a free-living setting, reducing challenges for future researchers. We believe that our experience will help future researchers develop successful mobile health (mHealth) systems that translate into reliable free-living deployments.
Interactivity
Gaze & Tongue: A Subtle, Hands-Free Interaction for Head-Worn Devices
Tan Gemicioglu, R. Michael Winters, Yu-Te Wang, Thom Gable, Ann Paradiso, Ivan Tashev
Gaze tracking allows hands-free and voice-free interaction with computers, and has gained more use recently in virtual and augmented reality headsets. However, it traditionally uses dwell time for selection tasks, which suffers from the Midas Touch problem. Tongue gestures are subtle, accessible and can be sensed non-intrusively using an IMU at the back of the ear, PPG and EEG. We demonstrate a novel interaction method combining gaze tracking with tongue gestures for gaze-based selection faster than dwell time and multiple selection options. We showcase its usage as a point-and-click interface in three hands-free games and a musical instrument.
Journals
Rapid Convergence: The Outcomes of Making PPE during a Healthcare Crisis
Kelly Mack, Megan Hofmann, Udaya Lakshmi, Jerry Cao, Nayha Auradkar, Rosa Arriaga, Scott Hudson, Jennifer Mankoff
The U.S. National Institute of Health (NIH) 3D Print Exchange is a public, open-source repository for 3D printable medical device designs with contributions from clinicians, expert-amateur makers, and people from industry and academia. In response to the COVID-19 pandemic, the NIH formed a collection to foster submissions of low-cost, locally-manufacturable personal protective equipment (PPE). We evaluated the 623 submissions in this collection to understand: what makers contributed, how they were made, who made them, and key characteristics of their designs. We found an immediate design convergence to manufacturing-focused remixes of a few initial designs affiliated with NIH partners and major for-profit groups. The NIH worked to review safe, effective designs but was overloaded by manufacturing-focused design adaptations. Our work contributes insights into: the outcomes of distributed, community-based medical making; the features that the community accepted as “safe” making; and how platforms can support regulated maker activities in high-risk domains.
Panels
Hardware is Hard – is it Worth it?
Steve Hodges, Per Ola Kristensson, Josiah Hester, Antonio Krüger, Jennifer Mankoff, Patrick Olivier, Yvonne Rogers
Within the field of technical human-computer interaction (HCI), there is a community of researchers who innovate in hardware: they build new device form factors, experiment with sensing, actuation and displays, and they deploy and study novel devices. Their work underpins many new and inclusive user experiences. A common perspective is that developing hardware is hard, especially in comparison to purely software-based activities. It typically involves a multitude of disciplines in addition to software, likely relies on third parties such as parts suppliers and manufacturing partners, has inherent delays that stifle agility, and it costs more. Is hardware really `harder’ though? And if it is, is innovation in hardware a worthwhile endeavor for the HCI community? This panel will discuss these topics with the aim of giving attendees a deeper understanding of the difficulties and benefits of hardware research in an HCI context.
Re-articulating North-South Collaborations in HCI
Reem Talhouk, Ebtisam Alabdulqader, Cat Kutay, Kagonya Awori Awori, Marisol Wong-Villacres, Neha Kumar, Tariq Zaman, Volker Wulf, Zainab AlMeraj, Shaimaa Lazem
Research connecting the ‘Global South’ and ‘Global North’ is not new to HCI. However, over the last few years we have seen a prominent shift in the ways we understand, represent and engage in North-South collaborations. Central to these discussions is the need to re-frame the nature of collaboration between and across geographies in which power dynamics, coloniality and the handling of differences are at the fore. In this panel, we will discuss experiences of HCI collaboration across the ‘Global South’ and ‘Global North’. The panel will unpack the joys, fluidity and tensions within such collaborations from various geographical perspectives, in an effort to de-homogenize the Global South, and provide ways forward for an HCI flavored re-articulation of collaboration across geo-politically established and epistemic borders.