Data Mining Practical Machine Learning Tools and Techniques

User Centered Design

Although rapid advances in machine learning have made it increasingly applicable to expert decision-making, the delivery of accurate algorithmic predictions alone is insufficient for effective human-AI collaboration. In this work, we investigate the key types of information medical experts desire when they are first introduced to a diagnostic AI assistant. In a qualitative lab study, we interviewed 21 pathologists before, during, and after being presented deep neural network (DNN) predictions for prostate cancer diagnosis, to learn the types of information that they desired about the AI assistant. Our findings reveal that, far beyond understanding the local, case-specific reasoning behind any model decision, clinicians desired upfront information about basic, global properties of the model, such as its known strengths and limitations, its subjective point-of-view, and its overall design objective--what it's designed to be optimized for. Participants compared these information needs to the collaborative mental models they develop of their medical colleagues when seeking a second opinion: the medical perspectives and standards that those colleagues embody, and the compatibility of those perspectives with their own diagnostic patterns. These findings broaden and enrich discussions surrounding AI transparency for collaborative decision-making, providing a richer understanding of what experts find important in their introduction to AI assistants before integrating them into routine practice.

https://dl.acm.org/doi/pdf/10.1145/3359206

"Hello AI": Uncovering the Onboarding Needs of Medical Practitioners for Human-AI Collaborative Decision-Making

Data-driven decision-making consequential to individuals raises important questions of accountability and justice. Indeed, European law provides individuals limited rights to 'meaningful information about the logic' behind significant, autonomous decisions such as loan approvals, insurance quotes, and CV filtering. We undertake three experimental studies examining people's perceptions of justice in algorithmic decision-making under different scenarios and explanation styles. Dimensions of justice previously observed in response to human decision-making appear similarly engaged in response to algorithmic decisions. Qualitative analysis identified several concerns and heuristics involved in justice perceptions including arbitrariness, generalisation, and (in)dignity. Quantitative analysis indicates that explanation styles primarily matter to justice perceptions only when subjects are exposed to multiple different styles --- under repeated exposure of one style, scenario effects obscure any explanation effects. Our results suggests there may be no 'best' approach to explaining algorithmic decisions, and that reflection on their automated nature both implicates and mitigates justice dimensions.

'It's Reducing a Human Being to a Percentage': Perceptions of Justice in Algorithmic Decisions

Designing interfaces or applications that move beyond the bounds of a single device screen enables new ways to engage with digital content. Research addressing the opportunities and challenges of interactions with multiple devices in concert is of continued focus in HCI research. To inform the future research agenda of this field, we contribute an analysis and taxonomy of a corpus of 510 papers in the cross-device computing domain. For both new and experienced researchers in the field we provide: an overview, historic trends and unified terminology of cross-device research; discussion of major and under-explored application areas; mapping of enabling technologies; synthesis of key interaction techniques spanning across multiple devices; and review of common evaluation strategies. We close with a discussion of open issues. Our taxonomy aims to create a unified terminology and common understanding for researchers in order to facilitate and stimulate future cross-device research.

/pdf/cross-device-taxonomy-survey-opportunities-and-challenges-of-2rubom7yex.pdf

Cross-Device Taxonomy: Survey, Opportunities and Challenges of Interactions Spanning Across Multiple Devices

Over the last 10 years, drones have become smaller, more durable, affordable, and easier to fly Their photo and videotaking capabilities have significantly improved In fact, the proliferation of drones is already happening, with new no-fly zones being developed in more territories Given current developments, we envision that everyone will be able to carry a pocket drone with them at all times, just like we do with smartphones today Drones appeal to users as they offer, among other things, a unique view of landscapes, wildlife, the user, and other people We conducted a survey in which we asked participants about their video and phototaking habits and how they could envision using a drone for these purposes Based on our findings, we envision systems in which nearby drones are available for personal and shared usage This allows having all the advantages of drones but leaves control over the airspace to regulators, thus enabling safely and respectfully flying over areas such as national parks or zoos Moreover, we envision shared drones as a means of sparking new social interactions

/pdf/enhancing-social-experiences-with-shared-drones-vju71h6rty.pdf

Enhancing Social Experiences with Shared Drones.

Proficiency-aware systems: Designing for user reflection in context-aware systems

Mountain Biking (MTB) is an increasingly popular outdoors activity which offers a unqiue connection to nature along with the health benefits of cardiovascular exercise. Yet, complex MTB technique is an entry barrier that often prevent novices from enjoying the sport. Developing interactive systems, which can support developing MTB proficiency can augment the outdoor experience and make the sport available to a larger group of users. To that end, we designed, implemented and evaluate MTBalance - a system which provides body posture feedback for beginner mountain bikers. Based on inertial tracking, MTBalance informs the user about how to correct their posture to improve MTB performance. We conducted a study in which we compared different feedback modalities for MTBalance. We observed that the system increased perceived balance awareness. Our work provides insights for designing body awareness systems for outdoor sports.

MTBalance: Assisting Novice Mountain Bikers with Real-Time Proprioceptive Feedback

Allowing users of interactive systems to reflect on their task proficiency is often incidental. This is unfortunate, as communicating meaningful task-related proficiency feedback could improve users’ awareness of their abilities and their willingness to improve. To highlight the feasibility of this concept, we evaluated how different methods of readability feedback impacted users during a text production task. In general, our results showed that having access to readability feedback allowed participants to reflect on their task solving approach, facilitating the users’ understanding of their proficiency. Revision-based methods are less distracting for the user than continuous feedback methods, while still offering high efficacy. Further, feedback should be paired with a subtle form of gamification elements. We envision this reflection-oriented design to user proficiency to be applicable to a variety of interactive systems, allowing for an improved and engaging user experience.

Your Text Is Hard to Read: Facilitating Readability Awareness to Support Writing Proficiency in Text Production

Recent research has shown that users increasingly seek meaning in technologies and that eudaimonic user experience (UX) is part of everyday encounters with technology. Yet, to date, there is no validated means to assess eudaimonic properties in interactive artefacts. We conceptualised, developed and validated a six-item questionnaire for measuring eudaimonic properties of technologies—the Eudaimonic Technology Experience Scale (ETES). Our scale includes two factors, which describe what aspects of a eudaimonic experience can be supported by technology: eudaimonic goals and self-knowlege. We consulted work in Human-Computer Interaction (HCI), psychology and philosophy to gather an initial set of concepts that could contribute to eudaimonic UX. We then built the scale based on expert interviews and exploratory factor analysis and verified its quality in a number of tests (confirmatory factor analysis, reliability and validity checks). ETES provides a standardised tool for identifying eudaimonic qualities in interactive systems and allows for rapidly comparing prototypes.

Paweł W. Woźniak

Papers

Enhancing Social Experiences with Shared Drones.

Proficiency-aware systems: Designing for user reflection in context-aware systems

MTBalance: Assisting Novice Mountain Bikers with Real-Time Proprioceptive Feedback

Your Text Is Hard to Read: Facilitating Readability Awareness to Support Writing Proficiency in Text Production

Quantifying Meaningful Interaction: Developing the Eudaimonic Technology Experience Scale