Downloaded 17 times
Uploaded bySeth Grimes
Emotion AI
The document discusses the necessity of emotional intelligence in computers for natural interactions, referencing the evolution of affective computing and various emotion models. It explores the distinctions between sentiment and emotion, the role of emotion mining, and how machines can synthesize emotional responses. Additionally, it touches on voice analysis in emotion recognition, emphasizing the importance of understanding human emotions for improving conversational AI and customer relationships.
More Related Content
Emotion AI
- 1. Emotion AI Seth Grimes AltaPlana Corporation @sethgrimes March 5, 2020
- 3.
- 4. “If we wantcomputers to be genuinely intelligent, to adapt to us and to interact naturally with us, then they will need to ability to recognize and express emotions, and to have what has come to be called ‘emotional intelligence.’” -- Rosalind Picard, Affective Computing, 1997 Affective Computing
- 5.
- 6. Bloom’s Taxonomy ofEducational Objectives, 1956: Affective, Cognitive & Psychomotor
- 7. « Le cœura ses raisons que la raison ne connaît point. » -- Blaise Pascal “All models are wrong, but some are useful.” -- George Box
- 8. Emotion models: Geneva EmotionWheel https://www.unige.ch/cisa/files/6914/6720/3988/2005_Scherer_SSI.pdf https://www.unige.ch/cisa/gew
- 9.
- 10. http://sentic.net Plutchik via SenticNet “Asa framework, SenticNet consists of a set of tools and techniques for sentiment analysis combining commonsense reasoning, psychology, linguistics, and machine learning.”
- 11. What about SentimentAnalysis? Text sourced… https://dl.acm.org/doi/10.1145/945645.945658, October 2003 https://dl.acm.org/doi/10.1561/1500000011, January 2008
- 12.
- 13. Sentiment -> Emotionpoints • Both sentiment and emotion are subjective. • Emotion models may be fine-grained and hierarchical. • Emotion categories aren’t orthogonal; emotion is compositional. • Sentiment is situational and not simply a one-dimensional projection of emotion. Consider…
- 15. Disclaimer I use ALOT of commercial product images in the slides that follow. These are illustrations and not meant as recommendations.
- 16.
- 17. Emotion AI “Emotion miningis the science of detecting, analyzing, and evaluating humans' feelings towards different events, issues, services, or any other interest.” Emotion synthesis enhances the ability of a machine to provide meaningful, contextual responses, by conveying an appropriate emotional state through words, voice, and expression. Emotion induction aims to evoke a certain emotional response or affective state. Examples …
- 19.
- 20.
- 21. “Parsing Text forEmotion Terms: Analysis & Visualization Using R” Emotion in Text: Parsing, Stats https://datascienceplus.com/parsing-text-for-emotion-terms-analysis-visualization-using-r/
- 22.
- 25.
- 26. Speech https://www.phon.ucl.ac.uk/courses/spsci/iss/week9.php “Voice cuesare commonly divided into those related to: (a) fundamental frequency (F0, a correlate of the perceived pitch), (b) vocal perturbation (short- term variability in sound production), (c) voice quality (a correlate of the perceived ‘timbre’), (d) intensity (a correlate of the perceived loudness), and (e) temporal aspects of speech (e.g., speech rate), as well as various combinations of these aspects (e.g., prosodic features).” http://www.scholarpedia.org/article/Speech_emotion_analysis
- 27.
- 28.
- 29.
- 31.
- 32. “Conversational Intelligence &Behavioral Prediction Insights from Voice: Our Oliver engine offers ASR+ with a sophisticated layer of emotion recognition metrics & behavioral KPIs, not only from what is being said but also from the how it is said.”
- 33. https://www.ipsoft.com/2019/08/29/emotional -intelligence-in-conversational-ai-why-amelia- is-a-leader/ “When Amelia isworking with customers or coworkers, she may sense frustration, anger, or even sadness. In these moments, she’s able to calibrate her tone and phraseology in order to be considerate of how her counterpart is feeling. With this emotional intelligence, she can build closer connections and relationships between a company and their customers and employees. “The language Amelia uses to interact with customers can vary from system to system and even from project to project. She can use slang, humor and even sarcasm, or she can speak in direct professional terms.”
- 35. MIT Nexi Robot,2008 SoftBank Pepper, 2015
- 36. Facial Coding SRI +Toyota
- 37.
- 38. Counterpoint 2 Affect recognition,a subset of facial recognition that claims to “read” our inner emotions by interpreting the micro-expressions on our face, has been a particular focus of growing concern in 2019—not only because it can encode biases, but because it lacks any solid scientific foundation to ensure accurate or even valid results.
- 39. Call for speakersthrough March 31: lt-innovate.org
- 40. Emotion AI Seth Grimes AltaPlana Corporation @sethgrimes March 5, 2020