Guidelines for Human-AI Interaction

被引:808
作者
Amershi, Saleema [1 ]
Weld, Dan [2 ,3 ]
Vorvoreanu, Mihaela [1 ]
Fourney, Adam [1 ]
Nushi, Besmira [1 ]
Collisson, Penny [1 ]
Suh, Jina [1 ]
Iqbal, Shamsi [1 ]
Bennett, Paul N. [1 ]
Inkpen, Kori [1 ]
Teevan, Jaime [1 ]
Kikin-Gil, Ruth [1 ]
Horvitz, Eric [1 ]
机构
[1] Microsoft, Redmond, WA 98052 USA
[2] Univ Washington, Paul G Allen Sch Comp Sci & Engn, Seattle, WA 98195 USA
[3] Microsoft Res, Redmond, WA USA
来源
CHI 2019: PROCEEDINGS OF THE 2019 CHI CONFERENCE ON HUMAN FACTORS IN COMPUTING SYSTEMS | 2019年
关键词
Human-AI interaction; AI-infused systems; design guidelines;
D O I
10.1145/3290605.3300233
中图分类号
TP3 [计算技术、计算机技术];
学科分类号
0812 ;
摘要
Advances in artificial intelligence (AI) frame opportunities and challenges for user interface design. Principles for humanAI interaction have been discussed in the human-computer interaction community for over two decades, but more study and innovation are needed in light of advances in AI and the growing uses of AI technologies in human-facing applications. We propose 18 generally applicable design guidelines for human-AI interaction. 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 believe the set of design guidelines can serve as a resource to practitioners working on the design of applications and features that harness AI technologies, and to researchers interested in the further development of guidelines for human-AI interaction design.
引用
收藏
页数:13
相关论文
共 39 条
[1]  
[Anonymous], P 2018 CHI C HUM FAC
[2]  
[Anonymous], 2012, QUALITATIVE RES DESI
[3]  
Baxter Kathy, 2017, MEDIUM
[4]   Intelligibility and accountability: Human considerations in context-aware systems [J].
Bellotti, V ;
Edwards, K .
HUMAN-COMPUTER INTERACTION, 2001, 16 (2-4) :193-212
[5]  
Bunt A., 2012, P 2012 ACM INT C INT, P169, DOI [10.1145/2166966.2166996, DOI 10.1145/2166966.2166996]
[6]   GenderMag: A Method for Evaluating Software's Gender Inclusiveness [J].
Burnett, Margaret ;
Stumpf, Simone ;
Macbeth, Jamie ;
Makri, Stephann ;
Beckwith, Laura ;
Kwan, Irwin ;
Peters, Anicia ;
Jernigan, William .
INTERACTING WITH COMPUTERS, 2016, 28 (06) :760-787
[7]   Why Do They Refuse to Use My Robot?: Reasons for Non-Use Derived from a Long-Term Home Study [J].
de Graaf, Maartje ;
Ben Allouch, Somaya ;
van Dijk, Jan .
PROCEEDINGS OF THE 2017 ACM/IEEE INTERNATIONAL CONFERENCE ON HUMAN-ROBOT INTERACTION (HRI'17), 2017, :224-233
[8]   On the Importance of Spatial Perception for the Design of Adaptive User Interfaces [J].
Deuschel, Tilman ;
Scully, Ted .
2016 IEEE 10TH INTERNATIONAL CONFERENCE ON SELF-ADAPTIVE AND SELF-ORGANIZING SYSTEMS (SASO), 2016, :70-79
[9]  
Dey A., 2002, PROC UIST 2002 C, P121, DOI [10.1145/571985.572003, DOI 10.1145/571985.572003]
[10]  
Findlater Leah., 2004, P SIGCHI C HUMAN FAC, P89, DOI [10.1145/985692.985704, DOI 10.1145/985692.985704]