HCI International 2014

Eva Hudlicka (short bio)
Psychometrix Associates, Inc. & School of Computer Science, University of Massachusetts, United States

Monday, 23 June 2014, 14:00 - 17:30

Objectives:

The objective of the tutorial is to provide an overview of state-of-the-art in computational affective modeling, and its relevance for affective user modeling and affect-adaptive HCI.

Content and Benefits:

Opportunities and needs for affect-adaptive interaction exist across a broad range of human-machine contexts, including intelligent training and tutoring, serious gaming, recommender systems, and varieties of interaction types with social robots and virtual affective agents. The consequent increasing demands for accurate user models are creating challenges for affective user modeling.

Typical existing affective user modeling approaches focus on the recognition of the user’s current affective state, and the use of this information to support immediate adaptation of system behavior to the user’s state. However, as the demands for system effectiveness and agent believability increase, affective user models will increasingly need to support not only immediate emotion recognition and adaptation, but also more extensive emotion understanding: a more in-depth understanding of the user’s affective profile, and the user’s affective needs and behavior over longer periods of time.

This tutorial will discuss how computational affective modeling methods can be applied to affective user modeling that supports emotion understanding.

The first half of the tutorial will introduce state-of-the-art approaches to computational affective modeling, focusing on the core processes of emotion generation via cognitive appraisal, and emotion effects modeling, and the associated computational tasks. Examples of cognitive-affective agent architectures will be discussed, and approaches to affective user modeling based on cognitive-affective architectures that aim to model the user will be explored.

The second half of the tutorial will focus on exploring several representative affective user models, and discussing the challenges associated with this approach to affective user modeling. Issues in construction and use of these types of models will be identified, and comparisons will be made with approaches to computational models of affective mind-reading, and their relevance to affective user modeling.

Target audience

Researchers and practitioners in HCI, affective HCI and affect-adaptive human-machine interaction. The material will be presented at an introductory level but familiarity with symbolic AI representational formalisms and inferencing is desirable.

Bio Sketch of Presenter:

Eva Hudlicka is a Principal Scientist and President of Psychometrix Associates, Inc., in Amherst, MA, and a Visiting Lecturer at the School of Computer Science, University of Massachusetts-Amherst. Her primary research focus is the development of computational models of emotion: both the cognitive processes involved in appraisal, and the effects of emotions on cognition. Her prior research includes affect-adaptive user interfaces, UI and visualization design, decision-support system development, and knowledge elicitation. Prior to founding Psychometrix Associates in 1995, she was a Senior Scientist at Bolt Beranek & Newman in Cambridge, MA. Dr. Hudlicka is an Associate Editor of the International Jnl. of Synthetic Emotions, and a member of the Editorial Board of the Intl. Jnl. of Machine Consciousness and the Oxford Series on “Cognitive Models and Architectures, and a Member of the IEEE Task Force on Player Satisfaction Modeling. She has served as a member of the National Research Council (NRC) committee on “Behavioral Modeling and Simulation”. Dr. Hudlicka has authored numerous journal, conference papers and book chapters in the area of affective computing, and has taught courses and tutorials in “Affective Computing” and “Computational Emotion Modeling”. She received her BS in Biochemistry from Virginia Tech, her MS from The Ohio State University in Computer Science, and her PhD in Computer Science from the University of Massachusetts-Amherst.