Affective Computing
summary
Defines affective computing as systems that recognize, interpret and simulate emotions and shows concrete tooling: Azure Face/Emotion API returning face rectangles and emotion probabilities (examples: surprise 83–99%), Azure Text Analytics for sentence-level sentiment, plus Amazon Rekognition and IBM emotion APIs. Describes biometric options (facial, speech, EEG/HR/skin conductance), applications in retail/medical/education/social, Effectiva claiming 6 million faces across 87 countries, Pepper robots and driver drowsiness detection, and mitigation tooling like Fairlearn for measured fairness tradeoffs.
AI-written summary · about
chapters (18)
- 0:00Introduction to affective computing
- 2:33Speaker background
- 3:57What is affective computing
- 5:03Psychology of emotions
- 13:20Measuring emotions
- 14:46Affective computing history
- 16:10Why affective computing now
- 18:00Emotion detection APIs demo
- 24:01Sentiment analysis demo
- 27:16Application scenarios
- 29:46Frontline companies and tools
- 33:02Artificial general intelligence
- 35:34AI future threats and hopes
- 37:20ML research community views
- 38:49Ethical AI and fairness
- 42:02Fairness tool Fairlearn
- 47:03Collective intelligence
- 49:09Conclusion and references
related talks
49mAffective Computing – Bringing Humans and Machines Closer Through Emotions
26mAffective Computing - What is it and why should I care?
34mEnhancing Customer Experiences with Emotional AI,
11mAmbient Intelligence and Emotionally Intelligent Devices
44mThe age of applied AI
39mAI + JavaScript Rocks
01h 05mAI for the Masses - Microsoft Cognitive Services
01h 05mMicrosoft Cognitive Services: Making AI Easy