Brain and physiological signals for multi-user modeling

Special session in ACII 2017 (Affective Computing and Intelligent Interaction)

Description

Emotional cues, generated subconsciously by the human body, have always been a crucial part of affective computing. Machines can learn about a person's affective state by analyzing measurements such as autonomic nervous system responses, neurophysiological measurements and gaze behavior. They can then act on the inferred information, adapting their own behavior, response or service based on the user's affective state.

Although emotions can be viewed as a social phenomenon, current physiological computing research is focused on emotions which are triggered by non-social stimuli. In the case of group interactions, emotions do not only develop in one’s mind but rather unfold according to the emotional expressions of the others. Consequently, the behavior, expressions and physiology of interacting people are known to be in synchrony during interactions. This inter-dependency of behavior and emotional expressions can in turn predict several properties of the social interaction such as grounding, mutual understanding, conflict, or social presence. Similarly, researchers in social neuro-science perform hyper-scanning to measure joint brain activities of people interacting with each other. The objective being to uncover brain areas and neural mechanisms supporting social processes.

With this special session we would like to develop research on multi-users’ modeling from neural and physiological sources. Here the concept of user modeling is defined broadly, including emotional, cognitive and social aspects which can be used for intelligent interactions. This special session targets researchers from computer science, neuro-science and psycho-physiology who are interested in the following research questions:

• What information about the user state and the quality of the interaction between users can be gained from (neuro-)physiological signals?
• How can that information, combined from several users, be used to interact adaptively with a machine?
• What is the effect of sharing physiological information with others?
• Which methods can be developed to reduce inter-users variability and improve user modeling?

To answer such research questions several databases are publicly available. Researchers who want to participate in the special session are welcome but not obliged to use those databases. Examples include:

EATMINT: https://eatmint.unige.ch

RECOLA: https://diuf.unifr.ch/diva/recola

MMDB: http://www.cbi.gatech.edu/mmdb/

Those databases are only examples and work on self-collected or other data are welcome.

Topics

• Collaborative brain-computer interfaces
• Tangible / social display of physiological and neural cues
• Social bio-feedback
• Assessment of social processes (conflict, empathy, relationship etc.)
• Assessment of the quality of interaction and collaboration
• Social neuroscience and psycho-physiology
• Emotion assessment, particularly social emotions
• Domain and transfer learning for building cross-participant models
• Methods for multiple user modeling (e.g. synchrony measures, dynamic multi-users' models, etc.)
• Applications of multi-user physiological computing
  
  

Important dates

Conference Dates: October 23-26

Paper Submission Deadline: May 2, 2017 extended to May 9, 2017

Reviews Provided to Authors: June 16, 2017

Author Rebuttals Due: June 23, 2017

Notification of Acceptance: July 14, 2017

Camera Ready Papers Due: August 18, 2017

Full paper authors should register By: August 7, 2017

Early registration deadline: September 1, 2017

Submission

Papers submitted to this Special Sessions have to be submitted following the same schedule and procedure as regular ACII papers (ACII paper submission). When submitting your paper please check the corresponding box for the Special Session on "Brain and physiological signals for multi-users’ modeling" in the ACII submission system.

The papers will undergo the same review process by anonymous and independent reviewers as the remaining ACII submissions.

Organizers