1 The Promise of Affective Computing Rosalind W. Picard, Sc.D., Fellow, IEEE Abstract—This chapter is adapted from an invited introduction written for the first issue of the IEEE Transactions on Affective Computing, telling personal stories and sharing viewpoints of a pioneer and visionary of the field of Affective Computing. This is not intended to be a thorough or a historical account of the development of the field for the author is not a historian and cannot begin to properly credit the extraordinary efforts of hundreds of people who helped bring this field into fruition. Instead, this chapter recounts experiences that contribute to this history, with an eye toward eliciting some of the pleasurable affective and cognitive responses that will be a part of the promise of Affective Computing. Index Terms—Affective Computing, Agents, Autism, Psychophysiology, Wearable Computing. ——————————  —————————— 1 INTRODUCTION ODIE is a young woman I am talking with at a fas- cinating annual retreat organized by autistic peo- ple for autistic people and their friends. Like most people on the autism spectrum (and many neuro- typicals, a term for people who don’t have a diag- nosed developmental disorder), she struggles with stress when unpredictable things happen. Tonight we are looking at what happened to her emotional arousal as measured by a wristband that gathers three signals – skin conductance, motion, and tem- perature (Fig. 1). Jodie was upset to learn that the event she was supposed to speak at was delayed from 8:00 to 8:30pm. She started pacing until her friend told her “Stop pacing, that doesn’t help you.” Many people don’t have an accurate read on what they are feeling (this is part of a condition known as alexithymia) and while she thought pacing helped, she wasn’t certain. So, she took his advice. She then started to make repetitive movements often seen in autism called “stimming,” and continued these until the event began at 8:30. In Fig. 1 we see her skin conductance on the top graph, going down when she was pacing, up when she was stimming, and hitting its highest peaks while she presents. The level also stays high afterward during other peo- ple’s presentations, when she stayed up front to handle problems with the audio-visual technology, including loud audio feedback. Collecting data related to emotional arousal is not new: For example, skin conductance has been studied over a hundred years. What is new, howev- er, is how technology can measure, communicate, adapt to, be adapted by, and transform emotion and how we think about it. Powerful new insights and changes can be achieved with these abilities. For example, Jodie collected her emotional arousal data wearing a stretchy wristband, clicked to upload it into a mobile viewer, and showed it to her friend (the one who had asked her to stop pacing). The first words spoken after checking the time stamps on the data display were his. He said, “I’m not going to tell you to stop pacing anymore.” The next morn- ing I saw the two of them again. This time, she was pacing and he sat quietly nearby letting her pace, typing on his laptop. The ability to communicate objective data related to her emotional arousal and activity – specifically her sympathetic nervous sys- tem activation of which skin conductance is a sensi- tive measure, prompted a change in his behavior. Mind you, she had told him in the moment of stress that she thought pacing was helping, but this did not change his behavior. Objective data about emo- tions carries much more power than self-reported subjective feelings. The convenience of a new affective computing technology can lead to new self-understanding as it did for Jodie. Objective data related to emotion is more believable than verbal reports about feelings. Shared affective data can improve communication between people and lead to better understanding and sometimes to beneficial changes in behavior: Jodie’s friend could now accept that her pacing might be helpful, and let Jodie pace. xxxx-xxxx/0x/$xx.00 © 200x IEEE ———————————————— R. W. Picard is with the MIT Media Laboratory, Cambridge, MA 02139. E- mail: picard@media.mit.edu. J