Skip to main content
Fachgebiete
Automobil + Motoren Bauwesen + Immobilien Business IT + Informatik Elektrotechnik + Elektronik Energie + Nachhaltigkeit Finance + Banking Management + Führung Marketing + Vertrieb Maschinenbau + Werkstoffe Versicherung + Risiko
DE
EN
Bücher
Zeitschriften
Themenseiten
Organisationspsychologie Projektmanagement Marketing Smart Manufacturing
Weitere Formate
Podcasts Webinare Technik Webinare Wirtschaft Kongresse Veranstaltungskalender Awards
Jetzt Einzelzugang starten
Zugang für Unternehmen
Referenzkunden
SLX-Digitalkonferenz: Zukunftswerkstatt 2024

Mehr Umsatz mit Top-Kontakten

Am 7. Mai erfahren Sie, wie Vertriebsteams Leadgenerierung, Leadnurturing und Leadstrategien effizient steuern können.
Erweiterte Suche
Anmelden
nach oben
Erschienen in:
Addressing the Challenges of COVID-19 Social Distancing Through Passive Wi-Fi and Ubiquitous Analytics: A Real World Deployment Kapitel lesen Erstes Kapitel lesen

2021 | OriginalPaper | Buchkapitel

Human-XAI Interaction: A Review and Design Principles for Explanation User Interfaces

verfasst von : Michael Chromik, Andreas Butz

Erschienen in: Human-Computer Interaction – INTERACT 2021

Verlag: Springer International Publishing

Einloggen

Aktivieren Sie unsere intelligente Suche, um passende Fachinhalte oder Patente zu finden.

search-config
loading …

Abstract

The interdisciplinary field of explainable artificial intelligence (XAI) aims to foster human understanding of black-box machine learning models through explanation-generating methods. Although the social sciences suggest that explanation is a social and iterative process between an explainer and an explainee, explanation user interfaces and their user interactions have not been systematically explored in XAI research yet. Therefore, we review prior XAI research containing explanation user interfaces for ML-based intelligent systems and describe different concepts of interaction. Further, we present observed design principles for interactive explanation user interfaces. With our work, we inform designers of XAI systems about human-centric ways to tailor their explanation user interfaces to different target audiences and use cases.

Sie haben noch keine Lizenz? Dann Informieren Sie sich jetzt über unsere Produkte:

Springer Professional "Wirtschaft+Technik"

Online-Abonnement

Mit Springer Professional "Wirtschaft+Technik" erhalten Sie Zugriff auf:

  • über 102.000 Bücher
  • über 537 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Maschinenbau + Werkstoffe
  • Versicherung + Risiko

Jetzt Wissensvorsprung sichern!

Jetzt informieren

Springer Professional "Technik"

Online-Abonnement

Mit Springer Professional "Technik" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 390 Zeitschriften

aus folgenden Fachgebieten:

  • Automobil + Motoren
  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Elektrotechnik + Elektronik
  • Energie + Nachhaltigkeit
  • Maschinenbau + Werkstoffe




 

Jetzt Wissensvorsprung sichern!

Jetzt informieren

Springer Professional "Wirtschaft"

Online-Abonnement

Mit Springer Professional "Wirtschaft" erhalten Sie Zugriff auf:

  • über 67.000 Bücher
  • über 340 Zeitschriften

aus folgenden Fachgebieten:

  • Bauwesen + Immobilien
  • Business IT + Informatik
  • Finance + Banking
  • Management + Führung
  • Marketing + Vertrieb
  • Versicherung + Risiko




Jetzt Wissensvorsprung sichern!

Jetzt informieren
Vorheriges Kapitel Effects of Interactivity and Presentation on Review-Based Explanations for Recommendations
Nächstes Kapitel Making SHAP Rap: Bridging Local and Global Insights Through Interaction and Narratives
Fußnoten
Literatur
1.
Abdul, A., Vermeulen, J., Wang, D., Lim, B.Y., Kankanhalli, M.: Trends and trajectories for explainable, accountable and intelligible systems. In: CHI 2018 (2018)
2.
Abdul, A., von der Weth, C., Kankanhalli, M., Lim, B.Y.: COGAM: measuring and moderating cognitive load in ML model explanations. In: CHI 2020 (2020)
3.
Adadi, A., Berrada, M.: Peeking inside the black-box: a survey on explainable artificial intelligence (XAI). IEEE Access 6, 52138–52160(2018)
4.
Alqaraawi, A., Schuessler, M., Weiss, P., Costanza, E., Berthouze, N.: Evaluating saliency map explanations for convolutional neural networks. In: IUI 2020 (2020)
5.
Amershi, S., et al.: Guidelines for human-AI interaction. In: CHI 2019 (2019)
6.
Andres, J., et al.: Introducing peripheral awareness as a neurological state for human-computer integration. In: CHI 2020 (2020)
7.
Arya, V., et al.: One explanation does not fit all: a toolkit and taxonomy of AI explainability techniques. arXiv (2019)
8.
Barria-Pineda, J., Brusilovsky, P.: Explaining educational recommendations through a concept-level knowledge visualization. In: IUI 2019 (2019)
9.
Binns, R., Van Kleek, M., Veale, M., Lyngs, U., Zhao, J., Shadbolt, N.: It’s reducing a human being to a percentage. In: CHI 2018 (2018)
10.
Bock, M., Schreiber, A.: Visualization of neural networks in virtual reality using unreal engine. In: VRST 2018 (2018)
11.
Bostandjiev, S., O’Donovan, J., Höllerer, T.: TasteWeights: a visual interactive hybrid recommender system. In: RecSys 2012 (2012)
12.
Buçinca, Z., Lin, P., Gajos, K.Z., Glassman, E.L.: Proxy tasks and subjective measures can be misleading in evaluating XAI systems. In: IUI 2020 (2020)
13.
Bunt, A., Lount, M., Lauzon, C.: Are explanations always important? A study of deployed, low-cost intelligent interactive systems. In: IUI 2012 (2012)
14.
Cai, C.J., Jongejan, J., Holbrook, J.: The effects of example-based explanations in a machine learning interface. In: IUI 2019 (2019)
15.
Chakraborti, T., Sreedharan, S., Grover, S., Kambhampati, S.: Plan explanations as model reconciliation: an empirical study. In: HRI 2019 (2019)
16.
Chen, L.: Adaptive tradeoff explanations in conversational recommenders. In: RecSys 2009 (2009)
17.
Chen, L., Wang, F.: Explaining recommendations based on feature sentiments in product reviews. In: IUI 2017 (2017)
18.
Cheng, H.F., et al.: Explaining decision-making algorithms through UI. In: CHI 2019 (2019)
19.
Chromik, M., Fincke, F., Butz, A.: Mind the (persuasion) gap: contrasting predictions of intelligent DSS with user beliefs. In: EICS 2020 Companion (2020)
20.
Cooper, A., Reimann, R., Cronin, D.: About Face 3: The Essentials of Interaction Design. Wiley, Hoboken (2007)
21.
Danilevsky, M., Qian, K., Aharonov, R., Katsis, Y., Kawas, B., Sen, P.: A survey of the state of explainable AI for natural language processing. arXiv (2020)
22.
Das, D., Chernova, S.: Leveraging rationales to improve human task performance. In: IUI 2020 (2020)
23.
Dodge, J., Liao, Q.V., Zhang, Y., Bellamy, R.K.E., Dugan, C.: Explaining models: an empirical study of how explanations impact fairness judgment. In: IUI 2019 (2019)
24.
Dodge, J., Penney, S., Hilderbrand, C., Anderson, A., Burnett, M.: How the experts do it: assessing and explaining agent behaviors in real-time strategy games. In: CHI 2018 (2018)
25.
Dominguez, V., Messina, P., Donoso-Guzmán, I., Parra, D.: The effect of explanations and algorithmic accuracy on visual recommender systems of artistic images. In: IUI 2019 (2019)
26.
Donkers, T., Kleemann, T., Ziegler, J.: Explaining recommendations by means of aspect-based transparent memories. In: IUI 2020 (2020)
27.
Doshi-Velez, F., Kim, B.: Towards a rigorous science of interpretable machine learning. arXiv (2017)
28.
Douglas, N., Yim, D., Kartal, B., Hernandez-Leal, P., Maurer, F., Taylor, M.E.: Towers of saliency: a reinforcement learning visualization using immersive environments. In: ISS 2019 (2019)
29.
Dudley, J.J., Kristensson, P.O.: A review of user interface design for interactive machine learning. ACM Trans. Interact. Intell, Syst (2018)CrossRef
30.
Ehsan, U., Tambwekar, P., Chan, L., Harrison, B., Riedl, M.O.: Automated rationale generation: a technique for explainable AI and its effects on human perceptions. In: IUI 2019 (2019)
31.
Eiband, M., Buschek, D., Kremer, A., Hussmann, H.: the impact of placebic explanations on trust in intelligent systems. In: CHI EA 2019 (2019)
32.
Feng, S., Boyd-Graber, J.: What can AI do for me? Evaluating machine learning interpretations in cooperative play. In: IUI 2019 (2019)
33.
34.
Fulton, L.B., Lee, J.Y., Wang, Q., Yuan, Z., Hammer, J., Perer, A.: Getting playful with explainable AI. In: CHI EA 2020 (2020)
35.
Garg, N., Schiebinger, L., Jurafsky, D., Zou, J.: Word embeddings quantify 100 years of gender and ethnic stereotypes. Proc. Natl Acad. Sci. 115(16), E3635–E3644 (2018)
36.
Guidotti, R., Monreale, A., Ruggieri, S., Turini, F., Giannotti, F., Pedreschi, D.: A survey of methods for explaining black box models. ACM Surv. 51, 1–42 (2018)
37.
Gunning, D.: DARPA’s XAI program. In: IUI 2019 (2019)
38.
Guzdial, M., et al.: Friend, collaborator, student, manager: how design of an AI-driven game level editor affects creators. In: CHI 2019 (2019)
39.
Hastie, H., Chiyah Garcia, F.J., Robb, D.A., Laskov, A., Patron, P.: MIRIAM: a multimodal interface for explaining the reasoning behind actions of remote autonomous systems. In: ICMI 2018 (2018)
40.
Herlocker, J.L., Konstan, J.A., Riedl, J.: Explaining collaborative filtering recommendations. In: CSCW 2000 (2000)
41.
Hohman, F., Head, A., Caruana, R., DeLine, R., Drucker, S.M.: Gamut: a design probe to understand how data scientists understand machine learning models. In: CHI 2019 (2019)
42.
Hornbaek, K., Oulasvirta, A.: What is interaction? In: CHI 2017 (2017)
43.
Horvitz, E.: Principles of mixed-initiative user interfaces. In: CHI 1999 (1999)
44.
Ishibashi, T., Nakao, Y., Sugano, Y.: Investigating audio data visualization for interactive sound recognition. In: IUI 2020 (2020)
45.
Kaur, H., et al.: Interpreting interpretability. In: CHI 2020 (2020)
46.
Kim, D.H., Hoque, E., Agrawala, M.: Answering questions about charts and generating visual explanations. In: CHI 2020 (2020)
47.
Kitchenham, B., Charters, S.: Guidelines for performing systematic literature reviews in software engineering (2007)
48.
Kleinerman, A., Rosenfeld, A., Kraus, S.: Providing explanations for recommendations in reciprocal environments. In: RecSys 2018 (2018)
49.
Knijnenburg, B.P., Bostandjiev, S., O’Donovan, J., Kobsa, A.: Inspectability and control in social recommenders. In: RecSys 2012 (2012)
50.
Kocaballi, A.B., Coiera, E., Berkovsky, S.: Revisiting habitability in conversational systems. In: CHI EA 2020 (2020)
51.
Koch, J., Lucero, A., Hegemann, L., Oulasvirta, A.: May AI? Design ideation with cooperative contextual bandits. In: CHI 2019 (2019)
52.
Krause, J., Perer, A., Ng, K.: Interacting with predictions: visual inspection of black-box machine learning models. In: CHI 2016 (2016)
53.
Law, E.L.C., Roto, V., Hassenzahl, M., Vermeeren, A.P.O.S., Kort, J.: Understanding, scoping and defining user experience. In: CHI 2009 (2009)
54.
Liao, Q.V., Gruen, D., Miller, S.: Questioning the AI: informing design practices for explainable AI user experiences. In: CHI 2020 (2020)
55.
Licklider, J.: Man-computer symbiosis. IRE Trans. Hum. Factors Electron. 1, 4–11 (1960)
56.
Lim, B.Y., Dey, A.K.: Weights of evidence for intelligible smart environments. In: UbiComp 2012 (2012)
57.
Linardatos, P., Papastefanopoulos, V., Kotsiantis, S.: Explainable AI: a review of machine learning interpretability methods (2020)
58.
Ludwig, J., Geiselman, E.: Intelligent pairing assistant for air operation centers. In: IUI 2012 (2012)
59.
Mai, T., et al.: Keeping it “Organized and Logical”. In: IUI 2020 (2020)
60.
Mikhail, M., Roegiest, A., Anello, K., Wei, W.: Dancing with the AI devil: investigating the partnership between lawyers and AI. In: CHIIR 2020 (2020)
61.
Millecamp, M., Htun, N.N., Conati, C., Verbert, K.: To Explain or not to explain: the effects of personal characteristics when explaining music recommendations. In: IUI 2019 (2019)
62.
Miller, T.: Explanation in artificial intelligence: insights from the social sciences. Artif. Intell. 267 1–38 (2019)
63.
Misztal-Radecka, J., Indurkhya, B.: Persona prototypes for improving the qualitative evaluation of recommendation systems. In: UMAP 2020 Adjunct (2020)
64.
Moore, J.D., Paris, C.: Requirements for an expert system explanation facility. Comput. Intell. 7, 367–370 (1991)
65.
Mueller, S.T., Hoffman, R.R., Clancey, W., Emrey, A., Klein Macrocognition, G.: Explanation in human-AI systems. arXiv (2019)
66.
Muhammad, K.I., Lawlor, A., Smyth, B.: A live-user study of opinionated explanations for recommender systems. In: IUI 2016 (2016)
67.
Murdoch, W.J., Singh, C., Kumbier, K., Abbasi-Asl, R., Yu, B.: Definitions, methods, and applications in interpretable machine learning. Proc. Natl Acad. Sci. 116, 22071–22080 (2019)
68.
Musto, C., Lops, P., de Gemmis, M., Semeraro, G.: Justifying recommendations through aspect-based sentiment analysis of users reviews. In: UMAP 2019 (2019)
69.
Norman, D., Draper, S.: User Centered System Design. New Perspectives on Human-Computer Interaction (1986)
70.
Nourani, M., et al.: Investigating the importance of first impressions and explainable AI with interactive video analysis. In: CHI EA 2020 (2020)
71.
O’Donovan, J., Smyth, B., Gretarsson, B., Bostandjiev, S., Höllerer, T.: PeerChooser: visual interactive recommendation. In: CHI 2008 (2008)
72.
Oh, C., et al.: Understanding how people reason about aesthetic evaluations of AI. In: DIS 2020 (2020)
73.
Oulasvirta, A., Hornbaek, K.: HCI research as problem-solving. In: CHI 2016 (2016)
74.
Páez, A.: The pragmatic turn in explainable artificial intelligence (XAI). Minds Mach. 29, 441–459 (2019)
75.
Patel, K., Bancroft, N., Drucker, S.M., Fogarty, J., Ko, A.J., Landay, J.: Gestalt: integrated support for implementation and analysis in ML. In: UIST 2010 (2010)
76.
Paudyal, P., Banerjee, A., Gupta, S.: On evaluating the effects of feedback for sign language learning using explainable AI. In: IUI 2020 (2020)
77.
Pilling, F., Akmal, H., Coulton, P., Lindley, J.: The process of gaining an AI legibility mark. In: CHI EA 2020 (2020)
78.
Poltrock, S.E., Steiner, D.D., Tarlton, P.N.: Graphic interfaces for knowledge-based system development (1986)
79.
Pu, P., Chen, L.: Trust building with explanation interfaces. In: IUI 2006 (2006)
80.
Robb, D.A., et al.: Exploring interaction with remote autonomous systems using conversational agents. In: DIS 2019 (2019)
81.
Schaekermann, M., Beaton, G., Sanoubari, E., Lim, A., Larson, K., Law, E.: Ambiguity-aware AI assistants for medical data analysis. In: CHI 2020 (2020)
82.
Schneeberger, T., Gebhard, P., Baur, T., André, E.: PARLEY: a transparent virtual social agent training interface. In: IUI, 2019 (2019)
83.
Schuessler, M., Weiß, P.: Minimalistic explanations: capturing the essence of decisions. In: CHI EA 2019 (2019)
84.
Shannon, C.E.: A mathematical theory of communication. Bell Syst. Tech. J. 5, 3–55 (1948)
85.
Shneiderman, B.: Bridging the gap between ethics and practice. ACM Trans. Interact. Intell. Syst. 10, 1–31 (2020)
86.
Shneiderman, B., Plaisant, C., Cohen, M., Jacobs, S., Elmqvist, N., Diakopoulos, N.: Confessions: grand challenges for HCI researchers. Interactions (2016)
87.
Simon, H.A.: Models of Bounded Rationality: Empirically Grounded Economic Reason, vol. 3. MIT Press, Cambridge (1997)
88.
Sklar, E.I., Azhar, M.Q.: Explanation through Argumentation. In: HAI 2018 (2018)
89.
Springer, A., Whittaker, S.: Progressive disclosure. ACM Trans. Interact. Intell. Syst. (2020)
90.
Stolterman, E., Wiltse, H., Chen, S., Lewandowski, V., Pak, L.: Analyzing artifact interaction complexity (2012)
91.
Tabrez, A., Agrawal, S., Hayes, B.: Explanation-based reward coaching to improve human performance via reinforcement learning. In: HRI 2019 (2019)
92.
Tintarev, N.: Explanations of recommendations. In: RecSys 2007 (2007)
93.
Tsai, C.H., Brusilovsky, P.: Evaluating visual explanations for similarity-based recommendations: user perception and performance. In: UMAP 2019 (2019)
94.
Vig, J., Sen, S., Riedl, J.: Tagsplanations: explaining recommendations using tags. In: IUI 2009 (2009)
95.
Vilone, G., Longo, L.: Explainable artificial intelligence: a systematic review. arXiv (2020)
96.
Wang, D., et al.: From human-human collaboration to human-AI collaboration. In: CHI EA 2020 (2020)
97.
Wang, D., Yang, Q., Abdul, A., Lim, B.Y.: Designing theory-driven user-centric explainable AI. In: CHI 2019 (2019)
98.
Wang, N., Pynadath, D.V., Hill, S.G.: Trust calibration within a human-robot team: comparing automatically generated explanations. In: HRI 2016 (2016)
99.
Weisz, J.D., Jain, M., Joshi, N.N., Johnson, J., Lange, I.: BigBlueBot: teaching strategies for successful human-agent interactions. In: IUI 2019 (2019)
100.
Wenskovitch, J., Dowling, M., North, C.: With respect to What? Simultaneous interaction with dimension reduction and clustering projections. In: IUI 2020 (2020)
101.
Wiegand, G., Schmidmaier, M., Weber, T., Liu, Y., Hussmann, H.: I drive - you trust: explaining driving behavior of autonomous cars. In: CHI EA 2019 (2019)
102.
Wolf, C.T.: Explainability scenarios: towards scenario-based XAI design. In: IUI 2019 (2019)
103.
Xie, J., Myers, C.M., Zhu, J.: Interactive visualizer to facilitate game designers in understanding machine learning. In: CHI EA 2019 (2019)
104.
Xie, Y., Chen, M., Kao, D., Gao, G., Chen, X.A.: CheXplain: enabling physicians to explore and understand data-driven medical imaging analysis. In: CHI 2020 (2020)
105.
Xu, W.: Toward human-centered AI: a perspective from human-computer interaction. Interactions (2019)
106.
Yang, F., Huang, Z., Scholtz, J., Arendt, D.L.: How do visual explanations foster end users’ appropriate trust in machine learning? In: IUI 2020 (2020)
107.
Yin, M., Wortman Vaughan, J., Wallach, H.: Understanding the effect of accuracy on trust in machine learning models. In: CHI 2019 (2019)
108.
Yu, B., Yuan, Y., Terveen, L., Wu, Z.S., Forlizzi, J., Zhu, H.: Keeping designers in the loop: communicating inherent algorithmic trade-offs across multiple objectives. In: DIS 2020 (2020)
109.
Zanker, M.: The Influence of knowledgeable explanations on users’ perception of a recommender system. In: RecSys 2012 (2012)
Metadaten
Titel
Human-XAI Interaction: A Review and Design Principles for Explanation User Interfaces
verfasst von
Michael Chromik
Andreas Butz
Copyright-Jahr
2021
Buch
Human-Computer Interaction – INTERACT 2021

Print ISBN: 978-3-030-85615-1

Electronic ISBN: 978-3-030-85616-8

Copyright-Jahr: 2021

DOI
https://doi.org/10.1007/978-3-030-85616-8_36

Neuer Inhalt

    Bildnachweise