Roman Klinger – Emotion Modelling in Text and Social Media: The Contribution of Psychological Models скачать в хорошем качестве

Roman Klinger – Emotion Modelling in Text and Social Media: The Contribution of Psychological Models

Emotion Modelling in Text and Social Media – The Contribution of Psychological Models – Roman Klinger (Institute for Natural Language Processing, University of Stuttgart) Lesson at the workshop and lectures "Sentiment Analysis in Literary Studies", 17th of February, 2021 Abstract: Emotion analysis from text includes a set of tasks, with emotion classification being the most prominent one. The task is to assign emotion categories to textual instances, for instance that a text expresses fear or joy. Most of the existing methods make use of state-of-the-art end-to-end machine learning, but do not take advantage of knowledge about the structure of emotions from psychology. In this talk, I present how the emotion component process model (which states that emotions consist of subjective feelings, physiological reactions, action tendencies, expressions, and cognitive appraisals) can be used to inform computational emotion classification decisions. Further, we will see how we can identify who is mentioned to be the experiencer of an emotion and which text segment describes the stimulus. This helps to get a comprehensive and deeper understanding of the emotion communicated in text. This is joint work with Laura Oberländer, Enrica Troiano, Jan Hofmann, Felix Casel, Evgeny Kim, and Amelie Heindl.