HCII Research at CHI 2019

April 29, 2019
2019 CHI Logo - weaving the threads of CHI

Thousands of the world’s top researchers, scientists, and designers are traveling to the ACM CHI Conference on Human Factors in Computing Systems (also known as CHI) this weekend. The premier international conference of Human-Computer Interaction will take place in Glasgow, UK from May 4-9, 2019.  

Human-Computer Interaction Institute researchers received two Best Paper awards and six Honorable Mention awards. Carnegie Mellon University’s most prolific writers this year were HCI Assistant Professor Lining Yao with 5 accepted papers and HCI PhD student Gierad Laput with 4 accepted papers. 

Carnegie Mellon University authors contributed to a total of 37 accepted papers, listed below. The only organization with more accepted papers than CMU in 2019 was the University of Washington.

 

Best Paper Best Paper Award  

“'Occupational Therapy is Making': Design Iteration and Digital Fabrication in Occupational Therapy"   -   Best Paper Award

Megan Hofmann (Carnegie Mellon University, Pittsburgh, PA, USA)
Kristin Williams (Carnegie Mellon University, Pittsburgh, PA, USA)
Toni Kaplan (Carnegie Mellon University, Pittsburgh, PA, USA)
Stephanie Valencia (Carnegie Mellon University, Pittsburgh, PA, USA)
Gabriella Han (Carnegie Mellon University, Pittsburgh, PA, USA)
Scott E. Hudson (Carnegie Mellon University, Pittsburgh, PA, USA)
Jennifer Mankoff (University of Washington, Seattle, WA, USA)
Patrick Carrington (Carnegie Mellon University, Pittsburgh, PA, USA)

Abstract:
Consumer-fabrication technologies potentially improve the effectiveness and adoption of assistive technology (AT) by engaging AT users in AT creation. However, little is known about the role of clinicians in this revolution. We investigate clinical AT fabrication by working as expert fabricators for clinicians over a four-month period. We observed and co-designed AT with four occupational Therapists at two clinics: a free clinic for uninsured clients, and a Veteran's Affairs Hospital. We find that existing fabrication processes, particularly with respect to rapid prototyping, do not align with clinical practice and its {do-no-harm} ethos. We recommend software solutions that would integrate into client care by: amplifying clinicians' expertise, revealing appropriate fabrication opportunities, and supporting adaptable fabrication.

"Unremarkable AI: Fitting Intelligent Decision Support into Critical, Clinical Decision-Making Processes"  -   Best Paper Award

Qian Yang, Carnegie Mellon University
Aaron Steinfeld, Carnegie Mellon University
John Zimmerman, Carnegie Mellon University

Abstract:
Clinical decision support tools (DST) promise improved healthcare outcomes by offering data-driven insights. While effective in lab settings, almost all DSTs have failed in practice.  Empirical research diagnosed poor contextual fit as the cause. This paper describes the design and field evaluation of a radically new form of DST. It automatically generates slides for clinicians’ decision meetings with subtly embedded machine prognostics. This design took inspiration from the notion of Unremarkable Computing, that by augmenting the users’ routines technology/AI can have significant importance for the users yet remain unobtrusive. Our field evaluation suggests clinicians are more likely to encounter and embrace such a DST. Drawing on their responses, we discuss the importance and intricacies of finding the right level of unremarkable-ness in DST design, and share lessons learned in prototyping critical AI systems as a situated experience.

 

Honorable MentionHonorable Mention Awards

"Sketching NLP: A Case Study of Exploring the Right Things To Design with Language Intelligence   -  Honorable Mention

Qian Yang (Carnegie Mellon University, Pittsburgh, PA, USA)
Justin Cranshaw (Microsoft Research, Redmond, WA, USA)
Saleema Amershi (Microsoft Research, Seattle, WA, USA)
Shamsi T. Iqbal (Microsoft Research, Redmond, WA, USA)
Jaime Teevan (Microsoft Research, Redmond, WA, USA)

Abstract:
This paper investigates how to sketch NLP-powered user experiences. Sketching is a cornerstone of design innovation. When Sketching, designers rapidly experiment with a number of abstract ideas using simple, tangible instruments such as drawings and paper prototypes. Sketching NLP-powered experiences, however, presents challenges, i.e. How to visualize abstract language interaction? How to ideate a broad range of technically feasible intelligent functionalities? As a first step towards understanding these challenges, we present a first-person account of our Sketching process when designing intelligent writing assistance. We detail the challenges we encountered and emergent solutions, such as a new format of wireframe for Sketching language interactions and a new wizard-of-oz-based NLP rapid prototyping method. Drawing on these findings, we discuss the importance of abstraction in Sketching and other implications.
 

"Sensing Posture-Aware Pen+Touch Interaction on Tablets"  -  Honorable Mention

Yang Zhang (Microsoft Research & Carnegie Mellon University, Redmond, WA, USA)
Michel Pahud (Microsoft Research, Redmond, WA, USA)
Christian Holz (Microsoft Research, Redmond, WA, USA)
Haijun Xia (Microsoft Research & University of Toronto, Redmond, WA, USA)
Gierad Laput (Microsoft Research & Carnegie Mellon University, Redmond, WA, USA)
Michael McGuffin (Microsoft Research & École de Technologie Supérieure, Redmond, WA, USA)
Xiao Tu (Microsoft Research, Redmond, WA, USA)
Andrew Mittereder (Microsoft Research, Redmond, WA, USA)
Fei Su (Microsoft Research, Redmond, WA, USA)
William Buxton (Microsoft Research, Redmond, WA, USA)
Ken Hinckley (Microsoft Research, Redmond, WA, USA)

Abstract:
Many status-quo interfaces for tablets with pen + touch input capabilities force users to reach for device-centric UI widgets at fixed locations, rather than sensing and adapting to the user-centric posture. To address this problem, we propose sensing techniques that transition between various nuances of mobile and stationary use via postural awareness. These postural nuances include shifting hand grips, varying screen angle and orientation, planting the palm while writing or sketching, and detecting what direction the hands approach from. To achieve this, our system combines three sensing modalities: 1) raw capacitance touchscreen images, 2) inertial motion, and 3) electric field sensors around the screen bezel for grasp and hand proximity detection. We show how these sensors enable posture-aware pen+touch techniques that adapt interaction and morph user interface elements to suit fine-grained contexts of body-, arm-, hand-, and grip-centric frames of reference.

"Interferi: Gesture Sensing using On-Body Acoustic Interferometry"  -  Honorable Mention

Yasha Iravantchi (Carnegie Mellon University, Pittsburgh, PA, USA)
Yang Zhang (Carnegie Mellon University, Pittsburgh, PA, USA)
Evi Bernitsas (Carnegie Mellon University, Pittsburgh, PA, USA)
Mayank Goel (Carnegie Mellon University, Pittsburgh, PA, USA)
Chris Harrison (Carnegie Mellon University, Pittsburgh, PA, USA)

Abstract:
Interferi is an on-body gesture sensing technique using acoustic interferometry. We use ultrasonic transducers resting on the skin to create acoustic interference patterns inside the wearer's body, which interact with anatomical features in complex, yet characteristic ways. We focus on two areas of the body with great expressive power: the hands and face. For each, we built and tested a series of worn sensor configurations, which we used to identify useful transducer arrangements and machine learning features. We created final prototypes for the hand and face, which our study results show can support eleven- and nine-class gestures sets at 93.4% and 89.0% accuracy, respectively. We also evaluated our system in four continuous tracking tasks, including smile intensity and weight estimation, which never exceed 9.5% error. We believe these results show great promise and illuminate an interesting sensing technique for HCI applications.

"Seekers, Providers, Welcomers, and Storytellers: Modeling Social Roles in Online Health Communities"  -  Honorable Mention

Diyi Yang (Carnegie Mellon University, Pittsburgh, PA, USA)
Robert E. Kraut (Carnegie Mellon University, Pittsburgh, PA, USA)
Tenbroeck Smith (American Cancer Society, Inc., Atlanta, GA, USA)
Elijah Mayfield (Carnegie Mellon University, Pittsburgh, PA, USA)
Dan Jurafsky (Stanford University, Stanford, CA, USA)

Abstract:
Participants in online communities often enact different roles when participating in their communities. For example, some in cancer support communities specialize in providing disease-related information or socializing new members. This work clusters the behavioral patterns of users of a cancer support community into specific functional roles. Based on a series of quantitative and qualitative evaluations, this research identified eleven roles that members occupy, such as welcomer and story sharer. We investigated role dynamics, including how roles change over members' lifecycles, and how roles predict long-term participation in the community. We found that members frequently change roles over their history, from ones that seek resources to ones offering help, while the distribution of roles is stable over the community's history. Adopting certain roles early on predicts members' continued participation in the community. Our methodology will be useful for facilitating better use of members' skills and interests in support of community-building efforts.
 

"The Channel Matters: Self-disclosure, Reciprocity and Social Support in Online Cancer Support Groups"  -  Honorable Mention

Diyi Yang (Carnegie Mellon University, Pittsburgh, PA, USA)
Zheng Yao (Carnegie Mellon University, Pittsburgh, PA, USA)
Joseph Seering (Carnegie Mellon University, Pittsburgh, PA, USA)
Robert Kraut (Carnegie Mellon University, Pittsburgh, PA, USA)

Abstract:
People with health concerns go to online health support groups to obtain help and advice. To do so, they frequently disclose personal details, many times in public. Although research in non-health settings suggests that people self-disclose less in public than in private, this pattern may not apply to health support groups where people want to get relevant help. Our work examines how the use of private and public channels influences members' self-disclosure in an online cancer support group, and how channels moderate the influence of self-disclosure on reciprocity and receiving support. By automatically measuring people's self-disclosure at scale, we found that members of cancer support groups revealed more negative self-disclosure in the public channels compared to the private channels. Although one's self-disclosure leads others to self-disclose and to provide support, these effects were generally stronger in the private channel. These channel effects probably occur because the public channels are the primary venue for support exchange, while the private channels are mainly used for follow-up conversations. We discuss theoretical and practical implications of our work.

"Implementing Multi-Touch Gestures with Touch Groups and Cross Events"   -   Honorable Mention

Steve Oney (University of Michigan, Ann Arbor, MI, USA)
Rebecca Krosnick (University of Michigan, Ann Arbor, MI, USA)
Joel Brandt (Adobe, Santa Monica, CA, USA)
Brad Myers (Carnegie Mellon University, Pittsburgh, PA, USA)

Abstract:
Multi-touch gestures can be very difficult to program correctly because they require that developers build high-level abstractions from low-level touch events. In this paper, we introduce programming primitives that enable programmers to implement multi-touch gestures in a more understandable way by helping them build these abstractions. Our design of these primitives was guided by a formative study, in which we observed developers' natural implementations of custom gestures. touch groups provide summaries of multiple fingers rather than requiring that programmers track them manually. Cross events allow programmers to summarize the movement of one or a group of fingers. We implemented these two primitives in two environments: a declarative programming system and in a standard imperative programming language. We found that these primitives are capable of defining nuanced multi-touch gestures, which we illustrate through a series of examples. Further, in two user evaluations of these programming primitives, we found that multi-touch behaviors implemented in these programming primitives are more understandable than those implemented with standard touch events.

 

All papers associated with Carnegie Mellon University at CHI 2019, organized by day

Monday, May 6, 2019

"Digital Fabrication of Soft Actuated Objects by Machine Knitting"

Lea Albaugh (Carnegie Mellon University, Pittsburgh, PA, USA)
Scott Hudson (Carnegie Mellon University, Pittsburgh, PA, USA)
Lining Yao (Carnegie Mellon University, Pittsburgh, PA, USA)

Abstract:
With recent interest in shape-changing interfaces, material-driven design, wearable technologies, and soft robotics, digital fabrication of soft actuatable material is increasingly in demand. Much of this research focuses on elastomers or non-stretchy air bladders. Computationally-controlled machine knitting offers an alternative fabrication technology which can rapidly produce soft textile objects that have a very different character: breathable, lightweight, and pleasant to the touch. These machines are well established and optimized for the mass production of garments, but compared to other digital fabrication techniques such as CNC machining or 3D printing, they have received much less attention as general purpose fabrication devices. In this work, we explore new ways to employ machine knitting for the creation of actuated soft objects. We describe the basic operation of this type of machine, then show new techniques for knitting tendon-based actuation into objects. We explore a series of design strategies for integrating tendons with shaping and anisotropic texture design. Finally, we investigate different knit material properties, including considerations for motor control and sensing.

"Exploring How Privacy and Security Factor into IoT Device Purchase Behavior"

Pardis Emami-Naeini (Carnegie Mellon University, Pittsburgh, PA, USA)
Henry Dixon (Carnegie Mellon University, Pittsburgh, PA, USA)
Yuvraj Agarwal (Carnegie Mellon University, Pittsburgh, PA, USA)
Lorrie Faith Cranor (Carnegie Mellon University, Pittsburgh, PA, USA)

Abstract:
Despite growing concerns about security and privacy of Internet of Things (IoT) devices, consumers generally do not have access to security and privacy information when purchasing these devices. We interviewed 24 participants about IoT devices they purchased. While most had not considered privacy and security prior to purchase, they reported becoming concerned later due to media reports, opinions shared by friends, or observing unexpected device behavior. Those who sought privacy and security information before purchase, reported that it was difficult or impossible to find. We asked interviewees to rank Factors they would consider when purchasing IoT devices; after features and price, privacy and security were ranked among the most important. Finally, we showed interviewees our prototype privacy and security label. Almost all found it to be accessible and useful, encouraging them to incorporate privacy and security in their IoT purchase decisions.

"Designing User Interface Elements to Improve the Quality and Civility of Discourse in Online Commenting Behaviors"

Joseph Seering (Carnegie Mellon University, Pittsburgh, PA, USA)
Tianmi Fang (Carnegie Mellon University, Pittsburgh, PA, USA)
Luca Damasco (Carnegie Mellon University, Pittsburgh, PA, USA)
Mianhong 'Cherie' Chen (Carnegie Mellon University, Pittsburgh, PA, USA)
Likang Sun (Carnegie Mellon University, Pittsburgh, PA, USA)
Geoff Kaufman (Carnegie Mellon University, Pittsburgh, PA, USA

Abstract:
Ensuring high-quality, civil social interactions remains a vexing challenge in many online spaces. In the present work, we introduce a novel approach to address this problem: using psychologically "embedded'' CAPTCHAs containing stimuli intended to prime positive emotions and mindsets. An exploratory randomized experiment (N = 454 Mechanical Turk workers) tested the impact of eight new CAPTCHA designs implemented on a simulated, politically charged comment thread. Results revealed that the two interventions that were the most successful at activating positive affect also significantly increased the positivity of tone and analytical complexity of argumentation in participants' responses. A focused follow-up experiment (N = 120 Mechanical Turk workers) revealed that exposure to CAPTCHAs featuring image sets previously validated to evoke low-arousal positive emotions significantly increased the positivity of sentiment and the levels of complexity and social connectedness in participants' posts. We offer several explanations for these results and discuss the practical and ethical implications of designing Interfaces to influence discourse in online forums.

"Career Mentoring in Online Communities: Seeking and Receiving Advice from an Online Community"

Maria Tomprou (Carnegie Mellon University, USA, PA, USA)
Laura Dabbish (Carnegie Mellon University, Pittsburgh, PA, USA)
Robert E. Kraut (Carnegie Mellon University, Pittsburgh, PA, USA)
Fannie Liu (Carnegie Mellon University, Pittsburgh, PA, USA)

Abstract:
Although people frequently seek mentoring or advice for their career, most mentoring is performed in person. Little research has examined the nature and quality of career mentoring online. To address this gap, we study how people use online Q&A forums for career advice. We develop a taxonomy of career advice requests based on a qualitative analysis of posts in a career-related online forum, identifying three key types: best practices, career threats, and time-sensitive requests. Our quantitative analysis of responses shows that both requesters and external viewers value general information, encouragement, and guidance, but not role modeling. We found no relation between the type of requests and features of responses, nor differences in responses valued by requesters versus external viewers. We present design recommendations for supporting online career advice exchange.

"Interferi: Gesture Sensing using On-Body Acoustic Interferometry - Honorable Mention"

Yasha Iravantchi (Carnegie Mellon University, Pittsburgh, PA, USA)
Yang Zhang (Carnegie Mellon University, Pittsburgh, PA, USA)
Evi Bernitsas (Carnegie Mellon University, Pittsburgh, PA, USA)
Mayank Goel (Carnegie Mellon University, Pittsburgh, PA, USA)
Chris Harrison (Carnegie Mellon University, Pittsburgh, PA, USA)

Abstract:
Interferi is an on-body gesture sensing technique using acoustic interferometry. We use ultrasonic transducers resting on the skin to create acoustic interference patterns inside the wearer's body, which interact with anatomical features in complex, yet characteristic ways. We focus on two areas of the body with great expressive power: the hands and face. For each, we built and tested a series of worn sensor configurations, which we used to identify useful transducer arrangements and machine learning features. We created final prototypes for the hand and face, which our study results show can support eleven- and nine-class gestures sets at 93.4% and 89.0% accuracy, respectively. We also evaluated our system in four continuous tracking tasks, including smile intensity and weight estimation, which never exceed 9.5% error. We believe these results show great promise and illuminate an interesting sensing technique for HCI applications.

 

"A-line: 4D Printing Morphing Linear Composite Structures"

Guanyun Wang (Carnegie Mellon University, Pittsburgh, PA, USA)
Ye Tao (Zhejiang University & Carnegie Mellon University, Hangzhou, China)
Ozguc Bertug Capunaman (Carnegie Mellon University, Pittsburgh, PA, USA)
Humphrey Yang (Carnegie Mellon University, Pittsburgh, PA, USA)
Lining Yao (Carnegie Mellon University, Pittsburgh, PA, USA)

Abstract:
This paper presents A-line, a 4D printing system for designing and fabricating morphing three-dimensional shapes out of simple linear elements. In addition to the commonly known benefit of 4D printing to save printing time, printing materials, and packaging space, A-line also takes advantage of the unique properties of thin lines, including their suitability for compliant mechanisms and ability to travel through narrow spaces and self-deploy or self-lock on site. A-line integrates a method of bending angle control in up to eight directions for one printed line segment, using a single type of thermoplastic material. A software platform to support the design, simulation and tool path generation is developed to support the design and manufacturing of various A-line structures. Finally, the design space of A-line is explored through four application areas, including line sculpting, compliant mechanisms, self-deploying, and self-locking structures.

"ElectroDermis: Fully Untethered, Stretchable, and Highly-Customizable Electronic Bandages"

Eric Markvicka (Carnegie Mellon University, Pittsburgh, PA, USA)
Guanyun Wang (Carnegie Mellon University, Pittsburgh, PA, USA)
Yi-Chin Lee (Carnegie Mellon University, Pittsburgh, PA, USA)
Gierad Laput (Carnegie Mellon University, Pittsburgh, PA, USA)
Carmel Majidi (Carnegie Mellon University, Pittsburgh, PA, USA)
Lining Yao (Carnegie Mellon University, Pittsburgh, PA, USA)

Abstract:
Wearables have emerged as an increasingly promising interactive platform, imbuing the human body with always-available computational capabilities. This unlocks a wide range of applications, including discreet information access, health monitoring, fitness, and fashion. However, unlike previous platforms, wearable electronics require structural conformity, must be comfortable for the wearer, and should be soft, elastic, and aesthetically appealing. We envision a future where electronics can be temporarily attached to the body (like bandages or party masks), but in functional and aesthetically pleasing ways. Towards this vision, we introduce ElectroDermis, a fabrication approach that simplifies the creation of highly-functional and stretchable wearable electronics that are conformal and fully untethered by discretizing rigid circuit boards into individual components. These individual components are wired together using stretchable electrical wiring and assembled on a spandex blend fabric, to provide high functionality in a robust form-factor that is reusable. We describe our system in detail— including our fabrication parameters and its operational limits—which we hope researchers and practitioners can leverage. We describe a series of example applications that illustrate the feasibility and utility of our system. Overall, we believe ElectroDermis offers a complementary approach to wearable electronics—one that places value on the notion of impermanence (i.e., unlike tattoos and implants), better conforming to the dynamic nature of the human body.

"Seekers, Providers, Welcomers, and Storytellers: Modeling Social Roles in Online Health Communities"   -   Honorable Mention

Diyi Yang (Carnegie Mellon University, Pittsburgh, PA, USA)
Robert E. Kraut (Carnegie Mellon University, Pittsburgh, PA, USA)
Tenbroeck Smith (American Cancer Society, Inc., Atlanta, GA, USA)
Elijah Mayfield (Carnegie Mellon University, Pittsburgh, PA, USA)
Dan Jurafsky (Stanford University, Stanford, CA, USA)

Abstract:
Participants in online communities often enact different roles when participating in their communities. For example, some in cancer support communities specialize in providing disease-related information or socializing new members. This work clusters the behavioral patterns of users of a cancer support community into specific functional roles. Based on a series of quantitative and qualitative evaluations, this research identified eleven roles that members occupy, such as welcomer and story sharer. We investigated role dynamics, including how roles change over members' lifecycles, and how roles predict long-term participation in the community. We found that members frequently change roles over their history, from ones that seek resources to ones offering help, while the distribution of roles is stable over the community's history. Adopting certain roles early on predicts members' continued participation in the community. Our methodology will be useful for facilitating better use of members' skills and interests in support of community-building efforts.

"SurfaceSight: A New Spin on Touch, User, and Object Sensing for IoT Experiences"

Gierad Laput (Carnegie Mellon University, Pittsburgh, PA, USA)
Chris Harrison (Carnegie Mellon University, Pittsburgh, PA, USA)

Abstract:
IoT appliances are gaining consumer traction, from smart thermostats to smart speakers. These devices generally have limited user interfaces, most often small buttons and touchscreens, or rely on voice control. Further, these devices know little about their surroundings – unaware of objects, people and activities happening around them. Consequently, interactions with these "smart" devices can be cumbersome and limited. We describe SurfaceSight, an approach that enriches IoT experiences with rich touch and object sensing, offering a complementary input channel and increased contextual awareness. For sensing, we incorporate LIDAR into the base of IoT devices, providing an expansive, ad hoc plane of sensing just above the surface on which devices rest. We can recognize and track a wide array of objects, including finger input and hand gestures. We can also track people and estimate which way they are facing. We evaluate the accuracy of these new capabilities and illustrate how they can be used to power novel and contextually-aware interactive experiences.

 

Tuesday, May 7, 2019

"Voice-Based Quizzes for Measuring Knowledge Retention in Under-Connected Populations"

Agha Ali Raza (Information Technology University, Lahore, Pakistan)
Zain Tariq (Information Technology University, Lahore, Pakistan)
Shan Randhawa (Information Technology University, Lahore, Pakistan)
Bilal Saleem (Information Technology University, Lahore, Pakistan)
Awais Athar (European Bioinformatics Institute (EMBL-EBI), Cambridge, United Kingdom)
Umar Saif (Information Technology University, Lahore, Pakistan)
Roni Rosenfeld (Carnegie Mellon University, Pittsburgh, PA, USA)

Abstract:
Information dissemination using automated phone calls allows reaching low-literate and tech-naive populations. Open challenges include rapid verification of expected knowledge gaps in the community, dissemination of specific information to address these gaps, and follow-up measurement of knowledge retention. We report Sawaal, a voice-based telephone service that uses audio-quizzes to address these challenges. Sawaal allows its open community of users to post and attempt multiple-choice questions and to vote and comment on them. Sawaal spreads virally as users challenge friends to quiz competitions. Administrator-posted questions allow confirming specific knowledge gaps, spreading correct information and measuring knowledge retention via rephrased, repeated questions. In 14 weeks and with no advertisement, Sawaal reached 3,433 users (120,119 calls) in Pakistan, who contributed 13,276 questions that were attempted 455,158 times by 2,027 users. Knowledge retention remained significant for up to two weeks. Surveys revealed that 71% of the mostly low-literate, young, male users were blind.

"'Occupational Therapy is Making': Clinical Rapid Prototyping and Digital Fabrication"  -  Best Paper award

Megan Hofmann (Carnegie Mellon University, Pittsburgh, PA, USA)
Kristin Williams (Carnegie Mellon University, Pittsburgh, PA, USA)
Toni Kaplan (Carnegie Mellon University, Pittsburgh, PA, USA)
Stephanie Valencia (Carnegie Mellon University, Pittsburgh, PA, USA)
Gabriella Han (Carnegie Mellon University, Pittsburgh, PA, USA)
Scott E. Hudson (Carnegie Mellon University, Pittsburgh, PA, USA)
Jennifer Mankoff (University of Washington, Seattle, WA, USA)
Patrick Carrington (Carnegie Mellon University, Pittsburgh, PA, USA)

Abstract:
Consumer-fabrication technologies potentially improve the effectiveness and adoption of assistive technology (AT) by engaging AT users in AT creation. However, little is known about the role of clinicians in this revolution. We investigate clinical AT fabrication by working as expert fabricators for clinicians over a four-month period. We observed and co-designed AT with four occupational Therapists at two clinics: a free clinic for uninsured clients, and a Veteran's Affairs Hospital. We find that existing fabrication processes, particularly with respect to rapid prototyping, do not align with clinical practice and its {do-no-harm} ethos. We recommend software solutions that would integrate into client care by: amplifying clinicians' expertise, revealing appropriate fabrication opportunities, and supporting adaptable fabrication.

"MessageOnTap: A Suggestive Interface to Facilitate Messaging-related Tasks"

Fanglin Chen (Human-Computer Interaction Institute, Pittsburgh, PA, USA)
Kewei Xia (Wuhan University, Wuhan, China)
Karan Dhabalia (Carnegie Mellon University, Pittsburgh, PA, USA)
Jason I. Hong (Carnegie Mellon University, Pittsburgh, PA, USA)

Abstract:
Text messages are sometimes prompts that lead to information related tasks, e.g. checking one's schedule, creating reminders, or sharing content. We introduce MessageOnTap, a suggestive inter-face for smartphones that uses the text in a conversation to suggest task shortcuts that can streamline likely next actions. When activated, MessageOnTap uses word embeddings to rank relevant external apps, and parameterizes associated task shortcuts using key phrases mentioned in the conversation, such as times, persons, or events. MessageOnTap also tailors the auto-complete dictionary based on text in the conversation, to streamline any text input.We first conducted a month-long study of messaging behaviors(N=22) that informed our design. We then conducted a lab study to evaluate the effectiveness of MessageOnTap's suggestive interface, and found that participants can complete tasks 3.1x faster withMessageOnTap than their typical task flow.

"Airport Accessibility and Navigation Assistance for People with Visual Impairments"

João Guerreiro (Carnegie Mellon University, Pittsburgh, PA, USA)
Dragan Ahmetovic (University of Turin & Carnegie Mellon University, Torino, Italy)
Daisuke Sato (IBM Research - Tokyo & Carnegie Mellon University, Tokyo, Japan)
Kris Kitani (Robotics Institute, Pittsburgh, PA, USA)
Chieko Asakawa (Carnegie Mellon University, Pittsburgh, PA, USA)

Abstract:
People with visual impairments often have to rely on the assistance of sighted guides in airports, which prevents them from having an independent travel experience. In order to learn about their perspectives on current airport accessibility, we conducted two focus groups that discussed their needs and experiences in-depth, as well as the potential role of assistive technologies. We found that independent navigation is a main challenge and severely impacts their overall experience. As a result, we equipped an airport with a Bluetooth Low Energy (BLE) beacon-based navigation system and performed a real-world study where users navigated routes relevant for their travel experience. We found that despite the challenging environment participants were able to complete their itinerary independently, presenting none to few navigation errors and reasonable timings. This study presents the first systematic evaluation posing BLE technology as a strong approach to increase the independence of visually impaired people in airports.

"Brick: Toward A Model for Designing Synchronous Colocated Augmented Reality Games"

Po Bhattacharyya (Carnegie Mellon University, Pittsburgh, PA, USA)
Radha Nath (Carnegie Mellon University, Pittsburgh, PA, USA)
Yein Jo (Entertainment Technology Center, Pittsburgh, PA, USA)
Ketki Jadhav (Carnegie Mellon University, Pittsburgh, PA, USA)
Jessica Hammer (Carnegie Mellon University, Pittsburgh, PA, USA)

Abstract:
Augmented reality (AR) games have been growing in popularity in recent years. However, current AR games offer limited opportunities for a synchronous multiplayer experience. This paper introduces a model for designing AR experiences in which players inhabit a shared, real-time augmented environment and can engage in synchronous and collaborative interactions with other players. We explored the development of this model through the creation of Brick, a two-player mobile AR game at the room scale. We refined Brick over multiple rounds of iteration, and we used our playtests to investigate a range of issues involved in designing shared-world AR games. Our findings suggest that there are five major categories of interactions in a shared-world AR system: single-player, intrapersonal, multiplayer, interpersonal, and environmental. We believe that this model can support the development of collaborative AR games and new forms of social gameplay.

"Casual Microtasking: Embedding Microtasks in Facebook"

Nathan Hahn (Carnegie Mellon University, Pittsburgh, PA, USA)
Shamsi T. Iqbal (Microsoft Research, Redmond, WA, USA)
Jaime Teevan (Microsoft Research, Redmond, WA, USA)

Abstract:
Microtasks enable people with limited time and context to contribute to a larger task. In this paper we explore casual microtasking, where microtasks are embedded into other primary activities so that they are available to be completed when convenient. We present a casual microtasking experience that inserts writing microtasks from an existing microwriting tool into the user's Facebook feed. From a two-week deployment of the system with nine people, we observe that casual microtasking enabled participants to get things done during their breaks, and that they tended to do so only after first engaging with Facebook's social content. Participants were most likely to complete the writing microtasks during periods of the day associated with low focus, and would occasionally use them as a springboard to open the original document in Word. These findings suggest casual microtasking can help people leverage spare micromoments to achieve meaningful micro-goals, and even encourage them to return to work.

"Towards Effective Foraging by Data Scientists to Find Past Analysis Choices"

Mary Beth Kery (Carnegie Mellon University, Pittsburgh, PA, USA)
Bonnie E John (Bloomberg L.P., New York, NY, USA)
Patrick O'Flaherty (Bloomberg L.P., New York, NY, USA)
Amber Horvath (Carnegie Mellon University, Pittsburgh, PA, USA)
Brad A. Myers (Carnegie Mellon University, Pittsburgh, PA, USA)

Abstract:
Data scientists are responsible for the analysis decisions they make, but it is hard for them to track the process by which they achieved a result. Even when data scientists keep logs, it is onerous to make sense of the resulting large number of history records full of overlapping variants of code, output, plots, etc. We developed algorithmic and visualization techniques for notebook code environments to help data scientists forage for information in their history. To test these interventions, we conducted a think-aloud evaluation with 15 data scientists, where participants were asked to find specific information from the history of another person's data science project. The participants succeed on a median of 80% of the tasks they performed. The quantitative results suggest promising aspects of our design, while qualitative results motivated a number of design improvements. The resulting system, called Verdant, is released as an open-source extension for JupyterLab.

"Implementing Multi-Touch Gestures with Touch Groups and Cross Events"   -  Honorable Mention

Steve Oney (University of Michigan, Ann Arbor, MI, USA)
Rebecca Krosnick (University of Michigan, Ann Arbor, MI, USA)
Joel Brandt (Adobe, Santa Monica, CA, USA)
Brad Myers (Carnegie Mellon University, Pittsburgh, PA, USA)

Abstract:
Multi-touch gestures can be very difficult to program correctly because they require that developers build high-level abstractions from low-level touch events. In this paper, we introduce programming primitives that enable programmers to implement multi-touch gestures in a more understandable way by helping them build these abstractions. Our design of these primitives was guided by a formative study, in which we observed developers' natural implementations of custom gestures. touch groups provide summaries of multiple fingers rather than requiring that programmers track them manually. Cross events allow programmers to summarize the movement of one or a group of fingers. We implemented these two primitives in two environments: a declarative programming system and in a standard imperative programming language. We found that these primitives are capable of defining nuanced multi-touch gestures, which we illustrate through a series of examples. Further, in two user evaluations of these programming primitives, we found that multi-touch behaviors implemented in these programming primitives are more understandable than those implemented with standard touch events.

"A Field Study of Computer-Security Perceptions Using Anti-Virus Customer-Support Chats"

Mahmood Sharif (Carnegie Mellon University, Pittsburgh, PA, USA)
Kevin A. Roundy (Symantec Research Labs, Culver City, CA, USA)
Matteo Dell'Amico (Symantec Research Labs, Sophia Antipolis, France)
Christopher Gates (Symantec Research Labs, Culver City, CA, USA)
Daniel Kats (Symantec Research Labs, Culver City, CA, USA)
Lujo Bauer (Carnegie Mellon University, Pittsburgh, PA, USA)
Nicolas Christin (Carnegie Mellon University, Pittsburgh, PA, USA)

Abstract:
Understanding users' perceptions of suspected computer-security problems can help us tailor technology to better protect users. To this end, we conducted a field study of users' perceptions using 189,272 problem descriptions sent to the customer-support desk of a large anti-virus vendor from 2015 to 2018. Using qualitative methods, we analyzed 650 problem descriptions to study the security issues users faced and the symptoms that led users to their own diagnoses. Subsequently, we investigated to what extent and for what types of issues user diagnoses matched those of experts. We found, for example, that users and experts were likely to agree for most issues, but not for attacks (e.g., malware infections), for which they agreed only in 44% of the cases. Our findings inform several user-security improvements, including how to automate interactions with users to resolve issues and to better communicate issues to users.

"BeamBand: Hand Gesture Sensing with Ultrasonic Beamforming"

Yasha Iravantchi (Carnegie Mellon University, Pittsburgh, PA, USA)
Mayank Goel (Carnegie Mellon University, Pittsburgh, PA, USA)
Chris Harrison (Carnegie Mellon University, Pittsburgh, PA, USA)

Abstract:
BeamBand is a wrist-worn system that uses ultrasonic beamforming for hand gesture sensing. Using an array of small transducers, arranged on the wrist, we can ensemble acoustic wavefronts to project acoustic energy at specified angles and focal lengths. This allows us to interrogate the surface geometry of the hand with inaudible sound in a raster-scan-like manner, from multiple viewpoints. We use the resulting, characteristic reflections to recognize hand pose at 8 FPS. In our user study, we found that BeamBand supports a six-class hand gesture set at 94.6% accuracy. Even across sessions, when the sensor is removed and reworn later, accuracy remains high: 89.4%. We describe our software and hardware, and future avenues for integration into devices such as smartwatches and VR controllers.

"Sensing Fine-Grained Hand Activity with Smartwatches"

Gierad Laput (Carnegie Mellon University, Pittsburgh, PA, USA)
Chris Harrison (Carnegie Mellon University, Pittsburgh, PA, USA)

Abstract:
Capturing fine-grained hand activity could make computational experiences more powerful and contextually aware. Indeed, philosopher Immanuel Kant argued, "the hand is the visible part of the brain." However, most prior work has focused on detecting whole-body activities, such as walking, running and bicycling. In this work, we explore the feasibility of sensing hand activities from commodity smartwatches, which are the most practical vehicle for achieving this vision. Our investigations started with a 50 participant, in-the-wild study, which captured hand activity labels over nearly 1000 worn hours. We then studied this data to scope our research goals and inform our technical approach. We conclude with a second, in-lab study that evaluates our classification stack, demonstrating 95.2% accuracy across 25 hand activities. Our work highlights an underutilized, yet highly complementary contextual channel that could unlock a wide range of promising applications.

"Designing Theory-Driven User-Centric Explainable AI"

Danding Wang, National University of Singapore
Qian Yang, Carnegie Mellon University
Ashraf Abdul, National University of Singapore
Brian Y. Lim, National University of Singapore

Abstract:
From healthcare to criminal justice, artificial intelligence (AI) is increasingly supporting high-consequence human decisions. This has spurred the field of explainable AI (XAI). This paper seeks to strengthen empirical application-specific investigations of XAI by exploring theoretical underpinnings of human decision making, drawing from the fields of philosophy and psychology. In this paper, we propose a conceptual framework for building human-centered, decision-theory-driven XAI based on an extensive review across these fields. Drawing on this framework, we identify pathways along which human cognitive patterns drives needs for building XAI and how XAI can mitigate common cognitive biases. We then put this framework into practice by designing and implementing an explainable clinical diagnostic tool for intensive care phenotyping and conducting a co-design exercise with clinicians. Thereafter, we draw insights into how this framework bridges algorithm-generated explanations and human decision-making theories. Finally, we discuss implications for XAI design and development.

"Desktop electrospinning: A Single Extruder 3D Printer for Producing Rigid Plastic and electrospun Textiles"

Michael L. Rivera, Carnegie Mellon University
Scott Hudson, Carnegie Mellon University

Abstract:
We present a new type of 3D printer that combines rigid plastic printing with melt electrospinning– a technique that uses electrostatic forces to create thin fibers from a molten polymer. Our printer enables custom-shaped textile sheets (similar in feel to wool felt) to be produced alongside rigid plastic using a single material (i.e., PLA) in a single process. We contribute open-source firmware, hardware specifications, and printing parameters to achieve melt electrospinning. Our approach offers new opportunities for fabricating interactive objects and sensors that blend the flexibility, absorbency and softness of produced electrospun textiles with the structure and rigidity of hard plastic for actuation, sensing, and tactile experiences.

 

Wednesday, May 8, 2019

"FiberWire: Embedding Electronic Function into 3D Printed Mechanically Strong, Lightweight Carbon Fiber Composite Objects"

Saiganesh Swaminathan (Carnegie Mellon University, Pittsburgh, PA, USA)
Kadri Bugra Ozutemiz (Carnegie Mellon University, Pittsburgh, PA, USA)
Carmel Majidi (Carnegie Mellon University, Pittsburgh, PA, USA)
Scott E. Hudson (Carnegie Mellon University, Pittsburgh, PA, USA)

Abstract:
3D printing offers significant potential in creating highly customized interactive and functional objects. However, at present ability to manufacture functional objects is limited by available materials (e.g., various polymers) and their process properties. For instance, many functional objects need stronger materials which may be satisfied with metal printers. However, to create wholly interactive devices, we need both conductors and insulators to create wiring, and electronic components to complete circuits. Unfortunately, the single material nature of metal printing, and its inherent high temperatures, preclude this. Thus, in 3D printed devices, we have had a choice of strong materials, or embedded interactivity, but not both. In this paper, we introduce a set of techniques we call FiberWire, which leverages a new commercially available capability to 3D print carbon fiber composite objects. These objects are light weight and mechanically strong, and our techniques demonstrate a means to embed circuitry for interactive devices within them. With FiberWire, we describe a fabrication pipeline takes advantage of laser etching and fiber printing between layers of carbon-fiber composite to form low resistance conductors, thereby enabling the fabrication of electronics directly embedded into mechanically strong objects. Utilizing the fabrication pipeline, we show a range of sensor designs, their performance characterization on these new materials and finally three fully printed example object that are both interactive and mechanically strong -- a bicycle handle bar with interactive controls, a swing and impact sensing golf club and an interactive game controller (Figure 1).

"Painting with CATS: Camera-Aided Texture Synthesis"

Ticha Sethapakdi (Carnegie Mellon University, Pittsburgh, PA, USA)
James McCann (Carnegie Mellon University, Pittsburgh, PA, USA)

Abstract:
We present CATS, a digital painting system that synthesizes textures from live video in real-time, short-cutting the typical brush- and texture- gathering workflow. Through the use of boundary-aware texture synthesis, CATS produces strokes that are non-repeating and blend smoothly with each other. This allows CATS to produce paintings that would be difficult to create with traditional art supplies or existing software. We evaluated the effectiveness of CATS by asking artists to integrate the tool into their creative practice for two weeks; their paintings and feedback demonstrate that CATS is an expressive tool which can be used to create richly textured paintings.

"Sensing Posture-Aware Pen+Touch Interaction on Tablets"  -  Honorable Mention

Yang Zhang (Microsoft Research & Carnegie Mellon University, Redmond, WA, USA)
Michel Pahud (Microsoft Research, Redmond, WA, USA)
Christian Holz (Microsoft Research, Redmond, WA, USA)
Haijun Xia (Microsoft Research & University of Toronto, Redmond, WA, USA)
Gierad Laput (Microsoft Research & Carnegie Mellon University, Redmond, WA, USA)
Michael McGuffin (Microsoft Research & École de Technologie Supérieure, Redmond, WA, USA)
Xiao Tu (Microsoft Research, Redmond, WA, USA)
Andrew Mittereder (Microsoft Research, Redmond, WA, USA)
Fei Su (Microsoft Research, Redmond, WA, USA)
William Buxton (Microsoft Research, Redmond, WA, USA)
Ken Hinckley (Microsoft Research, Redmond, WA, USA)

Abstract:
Many status-quo interfaces for tablets with pen + touch input capabilities force users to reach for device-centric UI widgets at fixed locations, rather than sensing and adapting to the user-centric posture. To address this problem, we propose sensing techniques that transition between various nuances of mobile and stationary use via postural awareness. These postural nuances include shifting hand grips, varying screen angle and orientation, planting the palm while writing or sketching, and detecting what direction the hands approach from. To achieve this, our system combines three sensing modalities: 1) raw capacitance touchscreen images, 2) inertial motion, and 3) electric field sensors around the screen bezel for grasp and hand proximity detection. We show how these sensors enable posture-aware pen+touch techniques that adapt interaction and morph user interface elements to suit fine-grained contexts of body-, arm-, hand-, and grip-centric frames of reference.

"Geodesy: Self-rising 2.5D Tiles by Printing along 2D Geodesic Closed Path"

Jianzhe Gu (Carnegie Mellon University, Pittsburgh, PA, USA)
David E. Breen (Carnegie Mellon University & Drexel University, Philadelphia, PA, USA)
Jenny Hu (Carnegie Mellon University, Pittsburgh, PA, USA)
Lifeng Zhu (Southeast University & Carnegie Mellon University, Pittsburgh, PA, USA)
Ye Tao (Zhejiang University & Carnegie Mellon University, Pittsburgh, PA, USA)
Tyson Van de Zande (Carnegie Mellon University, Pittsburgh, PA, USA)
Guanyun Wang (Carnegie Mellon University, Pittsburgh, PA, USA)
Yongjie Jessica Zhang (Carnegie Mellon University, Pittsburgh, PA, USA)
Lining Yao (Carnegie Mellon University, Pittsburgh, PA, USA)

Abstract:
Thermoplastic and Fused Deposition Modeling (FDM) based 4D printing are rapidly expanding to allow for space- and material-saving 2D printed sheets morphing into 3D shapes when heated. However, to our knowledge, all the known examples are either origami-based models with obvious folding hinges, or beam-based models with holes on the morphing surfaces. Morphing continuous double-curvature surfaces remains a challenge, both in terms of a tailored toolpath-planning strategy and a computational model that simulates it. Additionally, neither approach takes surface texture as a design parameter in its computational pipeline. To extend the design space of FDM-based 4D printing, in Geodesy, we focus on the morphing of continuous double-curvature surfaces or surface textures. We suggest a unique tool path - printing thermoplastics along 2D closed geodesic paths to form a surface with one raised continuous double-curvature tiles when exposed to heat. The design space is further extended to more complex geometries composed of a network of rising tiles (i.e., surface textures). Both design components and the computational pipeline are explained in the paper, followed by several printed geometric examples.

"Impact of Contextual Factors on Snapchat Public Sharing"  -  Honorable Mention

Hana Habib (Carnegie Mellon University, Pittsburgh, PA, USA)
Neil Shah (Snap Inc., Santa Monica, CA, USA)
Rajan Vaish (Snap Inc., Santa Monica, CA, USA)

Abstract:
Public sharing is integral to online platforms. This includes the popular multimedia messaging application Snapchat, on which public sharing is relatively new and unexplored in prior research. In mobile-first applications, sharing contexts are dynamic. However, it is unclear how context impacts users' sharing decisions. As platforms increasingly rely on user-generated content, it is important to also broadly understand user motivations and considerations in public sharing. We explored these aspects of content sharing through a survey of 1,515 Snapchat users. Our results indicate that users primarily have intrinsic motivations for publicly sharing Snaps, such as to share an experience with the world, but also have considerations related to audience and sensitivity of content. Additionally, we found that Snaps shared publicly were contextually different from those privately shared. Our findings suggest that content sharing systems can be designed to support sharing motivations, yet also be sensitive to private contexts.

"How Guiding Questions Facilitate Feedback Exchange in Project-Based Learning"

Amy Cook (Carnegie Mellon University, Pittsburgh, PA, USA)
Jessica Hammer (Carnegie Mellon University, Pittsburgh, PA, USA)
Salma Elsayed-Ali (William & Mary, Williamsburg, VA, USA)
Steven Dow (University of California, San Diego, La Jolla, CA, USA)

Abstract:
Peer feedback is essential for learning in project-based disciplines. However, students often need guidance when acting as either a feedback provider or a feedback receiver, both to gain from peer feedback and to criticize their peers' work. This paper explores how to more effectively scaffold this exchange such that peers more deeply engage in the feedback process. Within a game design course, we introduced different processes for feedback receivers to write questions to guide peer feedback. Feedback receivers wrote four main types of guiding questions: improve, share, brainstorm, critique. We found that "improve'' questions tended to lead to better feedback (more specific, critical, and actionable) than other question types, but feedback receivers wrote improve questions least often. We offer insights on how best to scaffold the question-writing process to facilitate peer feedback exchange.

"BBeep: A Sonic Collision Avoidance System for Blind Travellers and Nearby Pedestrians"

Seita Kayukawa (Carnegie Mellon University & Waseda University, Tokyo, Japan)
Keita Higuchi (University of Tokyo, Tokyo, Japan)
João Guerreiro (Carnegie Mellon University, Pittsburgh, PA, USA)
Shigeo Morishima (Waseda Research Institute for Science and Engineering, Tokyo, Japan)
Yoichi Sato (University of Tokyo, Tokyo, Japan)
Kris Kitani (Carnegie Mellon University, Pittsburgh, PA, USA)
Chieko Asakawa (Carnegie Mellon University & IBM Research, Yorktown Heights, NY, USA)

Abstract:
We present an assistive suitcase system, BBeep, for supporting blind people when walking through crowded environments. BBeep uses preemptive sound notifications to help clear a path by alerting both the user and nearby pedestrians about the potential risk of collision. BBeep triggers notifications by tracking pedestrians, predicting their future position in real-time, and provides sound notifications only when it anticipates a future collision. We investigate how different types and timings of sound affect nearby pedestrian behavior. In our experiments, we found that sound emission timing has a significant impact on nearby pedestrian trajectories when compared to different sound types. Based on these findings, we performed a real-world user study at an international airport, where blind participants navigated with the suitcase in crowded areas. We observed that the proposed system significantly reduces the number of imminent Collisions.

"Beyond Dyadic Interactions: Considering Chatbots as Community Members"

Joseph Seering (Carnegie Mellon University, Pittsburgh, PA, USA)
Michal Luria (Carnegie Mellon University, Pittsburgh, PA, USA)
Geoff Kaufman (Carnegie Mellon University, Pittsburgh, PA, USA)
Jessica Hammer (Carnegie Mellon University, Pittsburgh, PA, USA)

Abstract:
Chatbots have grown as a space for research and development in recent years due both to the realization of their commercial potential and to advancements in language processing that have facilitated more natural conversations. However, nearly all Chatbots to date have been designed for dyadic, one-on-one communication with users. In this paper we present a comprehensive review of research on Chatbots supplemented by a review of commercial and independent Chatbots. We argue that Chatbots' social roles and conversational capabilities beyond dyadic interactions have been underexplored, and that expansion into this design space could support richer social interactions in online communities and help address the longstanding challenges of maintaining, moderating, and growing these communities. In order to identify opportunities beyond dyadic interactions, we used research-through-design methods to generate more than 400 concepts for new social Chatbots, and we present seven categories that emerged from analysis of these ideas.

"Unremarkable AI: Fitting Intelligent Decision Support into Critical, Clinical Decision-Making Processes"  Best Paper Award

Qian Yang, Carnegie Mellon University
Aaron Steinfeld, Carnegie Mellon University
John Zimmerman, Carnegie Mellon University

Abstract:Clinical decision support tools (DST) promise improved healthcare outcomes by offering data-driven insights. While effective in lab settings, almost all DSTs have failed in practice.  Empirical research diagnosed poor contextual fit as the cause. This paper describes the design and field evaluation of a radically new form of DST. It automatically generates slides for clinicians’ decision meetings with subtly embedded machine prognostics. This design took inspiration from the notion of Unremarkable Computing, that by augmenting the users’ routines technology/AI can have significant importance for the users yet remain unobtrusive. Our field evaluation suggests clinicians are more likely to encounter and embrace such a DST. Drawing on their responses, we discuss the importance and intricacies of finding the right level of unremarkable-ness in DST design, and share lessons learned in prototyping critical AI systems as a situated experience.

"The Channel Matters: Self-disclosure, Reciprocity and Social Support in Online Cancer Support Groups"  -  Honorable Mention

Diyi Yang (Carnegie Mellon University, Pittsburgh, PA, USA)
Zheng Yao (Carnegie Mellon University, Pittsburgh, PA, USA)
Joseph Seering (Carnegie Mellon University, Pittsburgh, PA, USA)
Robert Kraut (Carnegie Mellon University, Pittsburgh, PA, USA)

Abstract:
People with health concerns go to online health support groups to obtain help and advice. To do so, they frequently disclose personal details, many times in public. Although research in non-health settings suggests that people self-disclose less in public than in private, this pattern may not apply to health support groups where people want to get relevant help. Our work examines how the use of private and public channels influences members' self-disclosure in an online cancer support group, and how channels moderate the influence of self-disclosure on reciprocity and receiving support. By automatically measuring people's self-disclosure at scale, we found that members of cancer support groups revealed more negative self-disclosure in the public channels compared to the private channels. Although one's self-disclosure leads others to self-disclose and to provide support, these effects were generally stronger in the private channel. These channel effects probably occur because the public channels are the primary venue for support exchange, while the private channels are mainly used for follow-up conversations. We discuss theoretical and practical implications of our work.

"Sketching NLP: A Case Study of Exploring the Right Things To Design with Language Intelligence   -  Honorable Mention

Qian Yang (Carnegie Mellon University, Pittsburgh, PA, USA)
Justin Cranshaw (Microsoft Research, Redmond, WA, USA)
Saleema Amershi (Microsoft Research, Seattle, WA, USA)
Shamsi T. Iqbal (Microsoft Research, Redmond, WA, USA)
Jaime Teevan (Microsoft Research, Redmond, WA, USA)

Abstract:
This paper investigates how to sketch NLP-powered user experiences. Sketching is a cornerstone of design innovation. When Sketching, designers rapidly experiment with a number of abstract ideas using simple, tangible instruments such as drawings and paper prototypes. Sketching NLP-powered experiences, however, presents challenges, i.e. How to visualize abstract language interaction? How to ideate a broad range of technically feasible intelligent functionalities? As a first step towards understanding these challenges, we present a first-person account of our Sketching process when designing intelligent writing assistance. We detail the challenges we encountered and emergent solutions, such as a new format of wireframe for Sketching language interactions and a new wizard-of-oz-based NLP rapid prototyping method. Drawing on these findings, we discuss the importance of abstraction in Sketching and other implications.

"ModiFiber: Two-Way Morphing Soft Thread Actuators for Tangible Interaction"

Jack Forman (Carnegie Mellon University, Pittsburgh, PA, USA)
Taylor Tabb (Carnegie Mellon University, Pittsburgh, PA, USA)
Youngwook Do (Carnegie Mellon University, Pittsburgh, PA, USA)
Meng-Han Yeh (Carnegie Mellon University, Pittsburgh, PA, USA)
Adrian Galvin (Carnegie Mellon University, Pittsburgh, PA, USA)
Lining Yao (Carnegie Mellon University, Pittsburgh, PA, USA)

Abstract:
Despite thin-line actuators becoming widely adopted in different Human-Computer Interaction (HCI) contexts, including integration into fabrics, paper art, hinges, soft robotics, and human hair, accessible line-based actuators are very limited beyond shape memory alloy (SMA) wire and motor-driven passive tendons. In this paper, we introduce a novel, yet simple and accessible, line-based actuator. ModiFiber is a twisted-then-coiled nylon thread actuator with a silicone coating. This composite thread actuator exhibits unique two-way reversible shrinking or twisting behaviors triggered by heat or electrical current (i.e., Joule heating). ModiFiber is soft, flexible, safe to operate and easily woven or sewn, hence it has a great potential as an embedded line-based actuator for HCI purposes. In this paper, we explain the material mechanisms and manufacturing approaches, followed by some performance tests and application demonstrations.

"Everyone Brings Their Grain of Salt": Designing for Low-Literate Parental Engagement with a Mobile Literacy Technology in Côte d'Ivoire

Michael A. Madaio (Carnegie Mellon University, Pittsburgh, PA, USA)
Fabrice Tanoh (Université Félix Houphouët-Boigny, Abidjan, Ivory Coast)
Axel Blahoua Seri (Institut de la Dignité et des Droits Humains, Abidjan, Ivory Coast)
Kaja Jasinska (University of Delaware, Newark, DE, USA)
Amy Ogan (Carnegie Mellon University, Pittsburgh, PA, USA)

Abstract:

Significant research has demonstrated the crucial role that parents play in supporting the development of children's literacy, but in contexts where adults may lack sufficient literacy in the target language, it is not clear how to most effectively scaffold parental support for children's literacy. Prior work has designed technologies to teach children literacy directly, but this work has not focused on designing for low-literate parents, particularly for multilingual and developing contexts. in this paper, we describe findings from a qualitative study conducted in several regions of rural Côte d'Ivoire to understand Ivorian parents' beliefs, desires, and preferences for French literacy. We discuss themes that emerged from these interviews, surrounding ideas of trust, collaboration, and culturally-responsive design, and we highlight implications for the design of technology to scaffold low-literate parental support for children's literacy.

 

 

Thursday, May 9, 2019

"Improving Fairness in Machine Learning Systems: What Do Industry Practitioners Need?"

Kenneth Holstein, Carnegie Mellon University
Jennifer Wortman Vaughan, Microsoft Research
Hal Daumé, Microsoft Research & University of Maryland
Miro Dudik, Microsoft Research
Hanna Wallach, Microsoft Research

Abstract:
The potential for machine learning (ML) systems to amplify social inequities and unFairness is receiving increasing popular and academic attention. A surge of recent work has focused on the development of algorithmic tools to assess and mitigate such unFairness. If these tools are to have a positive impact on industry practice, however, it is crucial that their design be informed by an understanding of real-world needs. Through 35 semi-structured interviews and an anonymous survey of 267 ML practitioners, we conduct the first systematic investigation of commercial product teams' challenges and needs for support in developing fairer ML systems. We identify areas of alignment and disconnect between the challenges faced by teams in practice and the solutions proposed in the fair ML research literature. Based on these findings, we highlight directions for future ML and HCI research that will better address practitioners' needs.