-------- Forwarded Message --------
Dear colleagues,
We are happy to introduce the minitrack on “*Explainable
Artificial
Intelligence (XAI)*” at *HICSS 55* (submission deadline: *June
15th*,
2021). We provide the opportunity for (extended) best papers of
this
minitrack to be *fast-tracked* to the journal* Electronic Markets
*(Special
Issue on “*Explainable and Responsible Artificial Intelligence*”*,
*CfP
will follow).
If you have any questions, please do not hesitate to contact
Christian
Meske (
christian.meske@fu-berlin.de)
Yours sincerely,
Christian Meske, Babak Abedin, Mathias Klier, Fethi Rabhi
*********************************************************************
*Call for Papers: “Explainable Artificial Intelligence (XAI)”
Minitrack at
the 55th Hawaii International Conference on System Sciences
(HICSS)*
*********************************************************************
The use of Artificial Intelligence (AI) in the context of decision
analytics and service science has received significant attention
in
academia and practice alike. Yet, much of the current efforts have
focused
on advancing underlying algorithms and not on decreasing the
complexity of
AI systems. AI systems are still “black boxes” that are difficult
to
comprehend—not only for developers, but particularly for users and
decision-makers. In addition, the development and use of AI is
associated
with many risks and pitfalls like biases in data or predictions
based on
spurious correlations (“Clever Hans” phenomena), which eventually
may lead
to malfunctioning or biased AI and hence technologically driven
discrimination.
This is where research on Explainable Artificial Intelligence
(XAI) comes
in. Also referred to as “transparent,” “interpretable,” or
“understandable
AI”, XAI aims to “produce explainable models, while maintaining a
high
level of learning performance (prediction accuracy); and enable
human users
to understand, appropriately, trust, and effectively manage the
emerging
generation of artificially intelligent partners”.
With a focus on decision support, this minitrack aims to explore
and extend
research on how to establish explainability of intelligent black
box
systems—machine learning-based or not. We especially look for
contributions
that investigate XAI from either a developer’s or user’s
perspective. We
invite submissions from all application domains, such as
healthcare,
finance, e-commerce, retail, public administration or others.
Technically
and method-oriented studies, case studies as well as design
science or
behavioral science approaches are welcome.
Topics of interest include, but are not limited to:
- The developers’ perspective on XAI
-
- XAI to open, control and evaluate black box algorithms
- Using XAI to identify bias in data
- Explainability and Human-in-the-Loop development of AI
- XAI to support interactive machine learning
- Prevention and detection of deceptive AI explanations
- XAI to discover deep knowledge and learn from AI
- Designing and deploying XAI systems
- Addressing user-centric requirements for XAI systems
- The users’ perspective on XAI
-
- Theorizing XAI-human interactions
- Presentation and personalization of AI explanations for
different
target groups
- XAI to increase situational awareness, compliance behavior and
task
performance
- XAI for transparency and unbiased decision making
- Impact of explainability on AI-based decision support systems
use
and adoption
- Explainability of AI in crisis situations
- Potential harm of explainability in AI
- Identifying user-centric requirements for XAI systems
- The governments’ perspective on XAI
-
- Explainability and transparency policy guidelines
- Evidence-based benefits and challenges of XAI implementations in
the public sector
- XAI and compliance
*Submission Deadline: *
June 15th, 2021 (Notification: until August 17th, 2021)
Further information for authors:
https://hicss.hawaii.edu/authors/
Link to minitrack descriptions:
https://hicss.hawaii.edu/tracks-54/decision-analytics-and-service-science/#explainable-artificial-intelligence-xai-minitrack
*Fast track:*
We provide the opportunity for (extended) best papers of this
minitrack to
be fast-tracked to the journal Electronic Markets (Special Issue
on
“Explainable and Responsible Artificial Intelligence”, CfP will
follow).
*Minitrack Co-Chairs: *
Christian Meske
Freie Universität Berlin
Babak Abedin
Macquarie University
Mathias Klier
University of Ulm
Fethi Rabhi
University of New South Wales
_______________________________________________
AISWorld mailing list
AISWorld@lists.aisnet.org