<html>
<head>
<meta http-equiv="Content-Type" content="text/html; charset=utf-8">
</head>
<body style="word-wrap: break-word; -webkit-nbsp-mode: space; line-break: after-white-space;" class="">
— Apologies for cross-posting — <br class="">
<br class="">
<b class=""><font size="3" class="">Special Issue "Explainable User Models"</font></b><br class="">
<br class="">
A special issue of <a href="https://www.mdpi.com/journal/mti" class="">Multimodal Technologies and Interaction</a> (ISSN 2414-4088).<br class="">
<br class="">
<b class="" style="font-size: 14px;">Important Dates & Facts:</b><br class="">
Abstract/title submission: ideally until <b class="">November 5, 2021</b><br class="">
Manuscripts due by: <b class="">February 20, 2022</b><br class="">
Notification to authors: <b class="">March 15, 2022</b><br class="">
<br class="">
<b class="">Website:</b> <a href="https://www.mdpi.com/journal/mti/special_issues/Explainable_User_Models" class="">https://www.mdpi.com/journal/mti/special_issues/Explainable_User_Models</a> <br class="">
<br class="">
<br class="">
<b class="" style="font-size: 14px;">Special Issue Information</b><br class="">
<br class="">
This special issue addresses research on Explainable User Models. As AI systems’ actions and decisions will significantly affect their users, it is important to be able to understand how an AI system represents its users. It is a well-known hurdle that many
AI algorithms behave largely as black boxes. One key aim of explainability is, therefore, to make the inner workings of AI systems more accessible and transparent.<br class="">
<br class="">
Such explanations can be helpful in the case when the system uses information about the user to develop a working representation of the user, and then uses this representation to adjust or inform system behavior. E.g., an educational system could detect whether students
have a more internal or external locus of control, a music recommender system could adapt the music it is playing to the current mood of a user, or an aviation system could detect the visual memory capacity of its pilots. However, when adapting to such user
models it is crucial that these models are accurately detected. Furthermore, for such explanations to be useful, they need to be able to explain or justify their representations of users in a human-understandable way. This creates a necessity for techniques
that will create models for the automatic generation of satisfactory explanations intelligible for human users interacting with the system.<br class="">
<br class="">
The scope of the special issue includes but is not limited to:<br class="">
<br class="">
<i class="">Detection and Modelling</i><br class="">
<div class=""><span class="Apple-tab-span" style="white-space: pre;"></span>• Novel ways of Modeling User Preferences<br class="">
</div>
<div class=""><span class="Apple-tab-span" style="white-space: pre;"></span>• Types of information to model (Knowledge, Personality, Cognitive differences, etc.)<br class="">
</div>
<div class=""><span class="Apple-tab-span" style="white-space: pre;"></span>• Distinguishing between stationary versus transient user models (e.g., Personality vs Mood)<br class="">
</div>
<div class=""><span class="Apple-tab-span" style="white-space: pre;"></span>• Context modeling (e.g., at work versus at home, lean in versus lean out activities)<br class="">
</div>
<div class=""><span class="Apple-tab-span" style="white-space: pre;"></span>• User models from heterogeneous sources (e.g., behavior, ratings, and reviews)<br class="">
</div>
<div class=""><span class="Apple-tab-span" style="white-space: pre;"></span>• Enrichment and Crowdsourcing for Explainable User Models<br class="">
</div>
<div class=""><br class="">
</div>
<i class="">Ethics</i><br class="">
<div class=""><span class="Apple-tab-span" style="white-space: pre;"></span>• Detection of sensitive or rarely reported attributes (e.g., gender, race, sexial orientation)<br class="">
</div>
<div class=""><span class="Apple-tab-span" style="white-space: pre;"></span>• Implicit user modeling versus explicit user modeling (e.g., questionnaires versus inference from behavior)<br class="">
</div>
<div class=""><span class="Apple-tab-span" style="white-space: pre;"></span>• User modeling for self actualization (e.g., user modeling to improve dietary or news consumption habits)<br class="">
</div>
<div class=""><br class="">
</div>
<i class="">Human understandability</i><br class="">
<div class=""><span class="Apple-tab-span" style="white-space: pre;"></span>• Metrics and methodologies for evaluating fitness for the purpose of explanations<br class="">
</div>
<div class=""><span class="Apple-tab-span" style="white-space: pre;"></span>• Balancing completeness and understandability for complex user models<br class="">
</div>
<div class=""><span class="Apple-tab-span" style="white-space: pre;"></span>• Explanations to mitigate human biases (e.g., confirmation bias, anchoring)<br class="">
</div>
<div class=""><span class="Apple-tab-span" style="white-space: pre;"></span>• Effect of user model explanation on subsequent user interaction (e.g., simulations, and novel evaluation methodologies)<br class="">
</div>
<div class=""><br class="">
</div>
<i class="">Effectiveness</i><br class="">
<div class=""><span class="Apple-tab-span" style="white-space: pre;"></span>• Analysis or comparison of context of use of explanation (e.g., risk, time pressure, error tolerance)<br class="">
</div>
<div class=""><span class="Apple-tab-span" style="white-space: pre;"></span>• Analysis of context of use of system (e.g., decision support, prediction)<br class="">
</div>
<div class=""><span class="Apple-tab-span" style="white-space: pre;"></span>• Analysis or comparison of effect of explaining in specific domains (e.g., education, health, recruitment, security)<br class="">
</div>
<div class=""><br class="">
</div>
<i class="">Adaptive presentation of the explanations</i><br class="">
<div class=""><span class="Apple-tab-span" style="white-space: pre;"></span>• For different types of user<br class="">
</div>
<div class=""><span class="Apple-tab-span" style="white-space: pre;"></span>• Interactive explanations<br class="">
</div>
<div class=""><span class="Apple-tab-span" style="white-space: pre;"></span>• Investigation of which presentational aspects are beneficial to tailor in the explanation (e.g., level of detail, terminology, modality text or graphics, level of interaction)<br class="">
</div>
<br class="">
<br class="">
Prof. Dr. Nava Tintarev<br class="">
Ms. Oana Inel<br class="">
Guest Editors
</body>
</html>