Affective Computing: A Roadmap Through Approaches, Technologies, and Data Analysis

Speaker:  Javier Gonzalez-Sanchez – Tempe, AZ, United States
Topic(s):  Human Computer Interaction

Abstract

Affect is inextricably related to human cognitive processes and expresses a great deal about human necessities; affect signals what matters to us and what we care about. Furthermore, affect impacts our rational decision-making and action selection. Providing computers with the capability to recognize, understand, and respond to human affective states would narrow the communication gap between the highly emotional human and the emotionally detached computer, enhancing their interactions. Computer applications in learning, healthcare, and entertainment stand to benefit from such capabilities. However, affect is a conceptual quantity with fuzzy boundaries and with substantial individual difference variations in expression and experience. This makes measuring affect a challenging task. 


This lecture provides a description and demonstration of devices and methodologies for automatically detecting affective states with a multimodal approach. It does not intend to present a comprehensive survey, but instead, a roadmap through the description and demonstration of a selection of devices and methodologies. It presents examples of data samples, collected in experimental studies, and discusses experiences using devices and methodologies in learning, entertainment, and healthcare scenarios. 


Lecture objectives include the following:

* Introduce the concepts and background behind affect measurement.

* Describe the devices used to detect affective states including brain-computer interfaces, gesture-based and posture-based affect recognition, eye-tracking, and physiological sensors.

* Describe the data that is gathered from each sensing device and its characteristics.

* Compare the pros and cons of the diverse devices

* Examine what it takes to gather, filter, and integrate affective data from a variety of sources.

* Describe approaches and tools for data analysis that correlate affect measurements with stimuli.

The lecture is open to researchers, practitioners, and educators interested in incorporating detection of affective states as part of their technology toolbox.

About this Lecture

Number of Slides:  65
Duration:  60 minutes
Languages Available:  English, Spanish
Last Updated: 

Request this Lecture

To request this particular lecture, please complete this online form.

Request a Tour

To request a tour with this speaker, please complete this online form.

All requests will be sent to ACM headquarters for review.