Tutorial title: A Tutorial on NLP for Affective Science: Exploring Fundamental Questions on Emotions through Language and Computation
Abstract: Natural Language Processing (NLP) has made much progress in the area of sentiment analysis. Yet, much of it has focused on automatically classifying pieces of text. In this tutorial, I will present an introduction to Affective Science and argue that NLP is uniquely positioned to contribute to it: to boldly explore a new frontier — to use language and computation to ask fundamental questions about how emotions and affect work, including:
- How do language and interoceptive (bodily) signals shape emotion?
- How do emotions impact health and behaviour?
- What agency do we have in regulating our emotions? etc.
As case studies in this nascent area of research (NLP for Affective Science), I will present my work on:
- WorryWords, Words of Warmth: Large lexicons of anxiety and warmth associations for English words; what they tell us about how we acquire language and how we express stereotypes.
- Emotion Dynamics and Emotion Granularity: Quantifying characteristics of emotion change and our ability to differentiate different emotions (using text); and its correlation with health outcomes.
- The Language of Interoception: Using language to shed light on the affectual connection between the body and mind.
I will conclude with a discussion of ethical considerations relevant to affective research, grounded in theory and best practices. This talk is a vision of Computational Affective Science that advances our understanding of emotion and human experience, builds useful applications, and plays an active role in navigating the societal implications of the powerful underlying technologies.