|
Rosalind W. Picard is founder and director of the
Affective Computing Research Group at the
Massachusetts Institute of Technology (MIT) Media
Laboratory and is co-director of the
Things That Think Consortium, the largest industrial
sponsorship organization at the lab. She holds a
Bachelors in Electrical Engineering with highest honors
from the Georgia Institute of Technology, and Masters
and Doctorate degrees, both in Electrical Engineering
and Computer Science, from the Massachusetts Institute
of Technology (MIT). She has been a member of the
faculty at the MIT Media Laboratory since 1991, with
tenure since 1998. Prior to completing her doctorate at
MIT, she was a Member of the Technical Staff at AT&T
Bell Laboratories where she designed VLSI chips for
digital signal processing and developed new methods of
image compression and analysis.
The author of over a hundred
peer-reviewed scientific articles in multidimensional
signal modeling, computer vision, pattern recognition,
machine learning, and human-computer interaction, Picard
is known internationally for pioneering research in
affective computing and, prior to that, for pioneering
research in content-based image and video retrieval. She
is recipient (with Tom Minka) of a best paper prize for
work on machine learning with multiple models (1998) and
is recipient (with Barry Kort and Rob Reilly) of a "best
theory paper" prize for their work on affect in human
learning (2001). Her award-winning book,
Affective Computing,
(MIT Press, 1997) lays the groundwork for giving
machines the skills of emotional intelligence. She and
her students have designed and developed a variety of
new sensors, algorithms, and systems for sensing,
recognizing, and responding respectfully to human
affective information, with applications in human and
machine learning, health, and human-computer
interaction. She was named a Fellow of the IEEE in
November 2004.
Picard has served on many
science and engineering program committees, editorial
boards, and review panels, and is presently serving on
the Editorial Board of User Modeling and User-Adapted
Interaction: The Journal of Personalization Research, as
well as on the advisory boards for the National Science
Foundation's division of Computers in Science and
Engineering (CISE) and for the Georgia Tech College of
Computing.
Picard works closely with
industry, and has consulted with companies such as
Apple, AT&T, BT, HP, i.Robot, and Motorola. She has
delivered keynote presentations or invited plenary talks
at over fifty science or technology events, and
distinguished lectures and colloquia at dozens of
universities and research labs internationally. Her
group's work has been featured in national and
international forums for the general public, such as The
New York Times, The London Independent, Scientific
American Frontiers, NPR's Tech Nation and The
Connection, ABC's Nightline and World News Tonight with
Peter Jennings, Time, Vogue, Voice of America Radio, New
Scientist, and BBC's "The Works" and "The Big Byte."
Picard lives in Newton, Massachusetts with her husband
and three energetic sons.
Abstract
Building an Affective Learning Companion
Rosalind W. Picard
MIT Media Laboratory 20 Ames St.; Cambridge, MA 02139
picard@media.mit.edu http://affect.media.mit.edu
About a half century ago, the computer became a model, metaphor and modelling tool privileging the cognitive over the affective, and engendering theories in which thinking and learning are viewed as information processing and affect is ignored or marginalised. In the last decade there has been an acceleration in efforts to redress this imbalance, developing technologies that can begin to measure and manage the role of affect, enabling new theories and interventions in which affect and cognition are appropriately integrated with one another. This invited keynote presents a vision for developing an automated learning companion that jointly supports a learner’s affective and cognitive needs. In particular, I will describe our efforts at MIT to invent several of the affective technologies to enable such a learning companion. The talk will show examples of the state of the art with respect to affect sensing and recognition and with respect to developing strategies for responding intelligently to learner affect.
Key words: Affect recognition, affective tutor, empathetic agents, frustration, learner emotion
Acknowledgments. I would like to thank past and present members of the MIT Affective Computing group for their many contributions designing and developing new kinds of technologies. Examples in this presentation result from collaborations with Ashish Kapoor, Win Burleson, Rana el Kaliouby, Carson Reynolds, Marc Strauss, Selene Mota, Hyungil Ahn, Shaundra Daily, Yuan Qi, John Rebula, Barry Kort, and Rob Reilly. We are indebted to Ken Perlin and John Lippincott for their development of the agent character shown in this talk. I would also like to gratefully acknowledge collaboration with Art Graesser’s group at Memphis. This work has been supported in part by the National Science Foundation under ITR 0325428, by the Media Lab Things That Think consortium, and by funds from NASA provided through Ahmed Noor. Any opinions, findings, conclusions, or recommendations expressed in this presentation are those of the presenter and do not necessarily reflect the views of the National Science Foundation or the offcial policies, either expressed or implied, of the sponsors or of the United States Government. |
