Guidelines for Human-AI Interaction

@article{Amershi2019GuidelinesFH,
  title={Guidelines for Human-AI Interaction},
  author={Saleema Amershi and Daniel S. Weld and Mihaela Vorvoreanu and Adam Fourney and Besmira Nushi and Penny Collisson and Jina Suh and Shamsi T. Iqbal and Paul N. Bennett and K. Quinn and J. Teevan and Ruth Kikin-Gil and E. Horvitz},
  journal={Proceedings of the 2019 CHI Conference on Human Factors in Computing Systems},
  year={2019}
}
Advances in artificial intelligence (AI) frame opportunities and challenges for user interface design. [...] Key Method These guidelines are validated through multiple rounds of evaluation including a user study with 49 design practitioners who tested the guidelines against 20 popular AI-infused products. The results verify the relevance of the guidelines over a spectrum of interaction scenarios and reveal gaps in our knowledge, highlighting opportunities for further research. Based on the evaluations, we…Expand
Designing AI to Work WITH or FOR People?
TLDR
This panel will bring together panelists with diverse backgrounds to engage the audience through the discussion of their shared or diverging visions on the future of human-AI interaction design. Expand
From Human-Computer Interaction to Human-AI Interaction: New Challenges and Opportunities for Enabling Human-Centered AI
TLDR
It is believed that promoting the HAII research and application will further enable the implementation of HCAI, enabling HCI professionals to address the unique issues of AI systems and develop human-centered AI systems. Expand
Transitioning to human interaction with AI systems: New challenges and opportunities for HCI professionals to enable human-centered AI
TLDR
A high-level literature review and a holistic analysis of current work in developing AI systems from an HCI perspective highlight the new changes introduced by AI technology and the new challenges that HCI professionals face when applying the human-centered AI (HCAI) approach in the development of AI systems. Expand
Player-AI Interaction: What Neural Network Games Reveal About AI as Play
TLDR
It is argued that games are an ideal domain for studying and experimenting with how humans interact with AI, and game and UX designers should consider flow to structure the learning curve of human-AI interaction, incorporate discovery-based learning to play around with the AI and observe the consequences. Expand
Challenges of Human-Aware AI Systems
TLDR
It is argued that the quest for human-aware AI systems broadens the scope of AI enterprise, necessitates and facilitates true inter-disciplinary collaborations, and can go a long way towards increasing public acceptance of AI technologies. Expand
Re-examining Whether, Why, and How Human-AI Interaction Is Uniquely Difficult to Design
TLDR
This paper identifies two sources of AI's distinctive design challenges: 1) uncertainty surrounding AI's capabilities, 2) AI's output complexity, spanning from simple to adaptive complex, and 3) four levels of AI systems. Expand
A Comparative Analysis of Industry Human-AI Interaction Guidelines
TLDR
This work has surveyed all of the design guidelines from each of these major companies and developed a single, unified structure of guidelines, giving developers a centralized reference of AI design guidelines. Expand
Beyond the Buzzwords: On the Perspective of AI in UX and Vice Versa
TLDR
The goal of the paper is to explore the relationship of AI and UX in concrete detail by referring to three case studies from the lab, taken from a project targeted at the development of a clinical decision support system. Expand
Artificial intelligence fairness in the context of accessibility research on intelligent systems for people who are deaf or hard of hearing
TLDR
The need for inclusion of data from people with disabilities in training sets, the lack of interpretability of AI systems, ethical responsibilities of access technology researchers and companies, and the need for appropriate evaluation metrics for AI-based access technologies are discussed. Expand
Researching AI Legibility through Design
TLDR
This paper thoroughly explores prior research in order to critically unpack the AI legibility problem space, and responds with design proposals whose aim is to enhance the legibility, to users, of systems using AI. Expand
...
1
2
3
4
5
...

References

SHOWING 1-10 OF 48 REFERENCES
Steps to take before intelligent user interfaces become real
  • K. Höök
  • Computer Science
  • Interact. Comput.
  • 2000
TLDR
A better understanding of the possible ways the interface can utilise intelligence to improve the interaction is needed and better tools that will enable an intelligent system to survive the full life cycle of a system. Expand
Are explanations always important?: a study of deployed, low-cost intelligent interactive systems
TLDR
The results of two studies examining the comprehensibility of, and desire for explanations with deployed, low-cost IIS reveal that comprehensibility is not always dependent on explanations, and the perceived cost of viewing explanations tends to outweigh the anticipated benefits. Expand
"Like Having a Really Bad PA": The Gulf between User Expectation and Experience of Conversational Agents
TLDR
This paper reports the findings of interviews with 14 users of CAs in an effort to understand the current interactional factors affecting everyday use, and finds user expectations dramatically out of step with the operation of the systems. Expand
How might people interact with agents
TLDR
The new crop of intelligent agents the authors different from the automated devices of earlier eras because of their computational power, they take over human tasks, and they interact with people in human-like ways-perhaps with a form of natural language, prrhaps with animated graphics or video. Expand
Principles of mixed-initiative user interfaces
Recent debate has centered on the relative promise of focusinguser-interface research on developing new metaphors and tools thatenhance users abilities to directly manipulate objects versusdirectingExpand
Adaptive interfaces and agents
As its title suggests, this chapter covers a broad range of interactive systems. But they all have one idea in common: that it can be worthwhile for a system to learn something about each individualExpand
The Lumière Project: Bayesian User Modeling for Inferring the Goals and Needs of Software Users
TLDR
This work reviews work on Bayesian user models that can be employed to infer a user's needs by considering a users' background, actions, and queries and proposes an overall architecture for an intelligent user interface. Expand
Exploring the design space for adaptive graphical user interfaces
TLDR
This paper designs and implemented three adaptive graphical interfaces and evaluated them in two experiments along with a non-adaptive baseline and discusses how different design choices and interactions affect the success of adaptive graphical user interfaces. Expand
Intelligibility and Accountability: Human Considerations in Context-Aware Systems
TLDR
It is argued that there are human aspects of context that cannot be sensed or even inferred by technological means, so context-aware systems cannot be designed simply to act on the authors' behalf, and will have to be able to defer to users in an efficient and nonobtrusive fashion. Expand
Assessing demand for intelligibility in context-aware applications
TLDR
Why users demand certain types of information is discussed, and design implications on how to provide different intelligibility types to make context-aware applications intelligible and acceptable to users are provided. Expand
...
1
2
3
4
5
...