Abstract
Computational linguistics has witnessed a surge of interest in approaches to emotion and affect analysis, tackling problems that extend beyond sentiment analysis in depth and complexity. This area involves basic emotions (such as joy, sadness, and fear) as well as any of the hundreds of other emotions humans are capable of (such as optimism, frustration, and guilt), expanding into affective conditions, experiences, and activities. Leveraging linguistic data for computational affect and emotion inference enables opportunities to address a range of affect-related tasks, problems, and non-invasive applications that capture aspects essential to the human condition and individuals’ cognitive processes. These efforts enable and facilitate human-centered computing experiences, as demonstrated by applications across clinical, socio-political, artistic, educational, and commercial domains. Efforts to computationally detect, characterize, and generate emotions or affect-related phenomena respond equally to technological needs for personalized, micro-level analytics and broad-coverage, macro-level inference, and they have involved both small and massive amounts of data.While this is an exciting area with numerous opportunities for members of the ACL community, a major obstacle is its intersection with other investigatory traditions, necessitating knowledge transfer. This tutorial comprehensively integrates relevant concepts and frameworks from linguistics, cognitive science, affective computing, and computational linguistics in order to equip researchers and practitioners with the adequate background and knowledge to work effectively on problems and tasks either directly involving, or benefiting from having an understanding of, affect and emotion analysis.There is a substantial body of work in traditional sentiment analysis focusing on positive and negative sentiment. This tutorial covers approaches and features that migrate well to affect analysis. We also discuss key differences from sentiment analysis, and their implications for analyzing affect and emotion.The tutorial begins with an introduction that highlights opportunities, key terminology, and interesting tasks and challenges (1). The body of the tutorial covers characteristics of emotive language use with emphasis on relevance for computational analysis (2); linguistic data—from conceptual analysis frameworks via useful existing resources to important annotation topics (3); computational approaches for lexical semantic emotion analysis (4); computational approaches for emotion and affect analysis in text (5); visualization methods (6); and a survey of application areas with affect-related problems (7). The tutorial concludes with an outline of future directions and a discussion with participants about the areas relevant to their respective tasks of interest (8).Besides attending the tutorial, tutorial participants receive electronic copies of tutorial slides, a complete reference list, as well as a categorized annotated bibliography that concentrates on seminal works, recent important publications, and other products and resources for researchers and developers.