With Roman Klinger (Institute for Natural Language Processing, University of Stuttgart), Rachele Sprugnoli (University Cattolica del Sacro Cuore), Katrin Dennerlein (Institute for German Philology, University of Würzburg) and Thomas Schmidt (Institute for Information and Media, Language and Culture, University of Regensburg)
Program and Abstracts
In the context of the event Sentiment Analysis in Literary Studies organized by the project team of Distant Spectators. Distant Reading for Periodicals of the Enlightenment, funded by CLARIAH-AT, we invite you to the following open keynote lectures (with required registration):
Wednesday, 17.02.2021, 15:30 – 16:30h (CET)
Emotion Modelling in Text and Social Media – The Contribution of Psychological Models – Roman Klinger (Institute for Natural Language Processing, University of Stuttgart)
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.
Thursday, 18.02.2021, 15:30 – 16:30h (CET)
Sentiment Analysis for Latin: a Journey from Seneca to Thomas Aquinas
– Rachele Sprugnoli (University Cattolica del Sacro Cuore)
While the main applications of resources and tools for sentiment analysis typically fall within the scope of fields like customer experience and social media monitoring, there is an increasing interest in extending their range to texts written in ancient and historical languages. Such interest mirrors the substantial growth of the area dedicated to building and using linguistic resources for these languages, which are essential for accessing and understanding the Classical tradition.
In this talk, we will present the methodology we followed to create and evaluate a new set of Latin sentiment lexicons, and the process of inclusion of a prior polarity lexicon of Latin lemmas in a knowledge base of interoperable linguistic resources developed within the ERC project “LiLa: Linking Latin”. We will discuss the main challenges we face when working with ancient languages (e.g., lack of native speakers, limited amount of data, unusual textual genres for the sentiment analysis task, such as philosophical or documentary texts) and we will describe two use cases underscoring the importance of an interdisciplinary approach combining computational linguistics, semantic web and humanities practices.
Friday, 19.02.2021, 15:30 – 16:30h (CET)
Annotating and quantifying sentiment and emotions in German plays from around 1800
– Katrin Dennerlein (Institute for German Philology, University of Würzburg) and Thomas Schmidt (Institute for Information and Media, Language and Culture, University of Regensburg)
We report on our experiences with Sentiment Analysis in historic German plays and about the ongoing project “Emotions in Drama” which is a project of the priority program SPP 2207 Computational Literary Studies (CLS), funded by the German Research Foundation (DFG). We talk about the challenges we encountered in our work with lexicon-based sentiment analysis and the creation of sentiment analysis calculation and visualization tools for the Digital Humanities community. Furthermore, we report on the problems and difficulties of developing emotion annotation schemes and annotating emotions in plays with the goal to satisfy the literary studies' perspective as well as the computer science perspective equally.
The lectures will be held online. To get the access link and to participate, it is required to register before February 17th under the following link: https://forms.gle/EpfSDdxenL9kF2BV8.
Roman Klinger is a senior lecturer at the Institute for Natural Language Processing (IMS) at the University of Stuttgart. He studied computer science with a minor in psychology, holds a Ph.D. in computer science from TU Dortmund University (2011), and received the venia legendi in computer science in Stuttgart (2020). Before moving to Stuttgart, he worked at the University of Bielefeld, at the Fraunhofer Institute for Algorithms and Scientific Computing, and the University of Massachusetts Amherst. Roman Klinger’s vision is to enable computers to understand and generate text regarding both factual and non-factual information. This finds application in interdisciplinary research, including biomedical text mining, digital humanities, modelling psychological concepts (like emotions) in language, and social media mining. These topics often constitute novel challenges to existing machine learning methods. Therefore, he and his group also contribute to the fields of probabilistic and deep machine learning.
Rachele Sprugnoli is a postdoctoral researcher at Università Cattolica del Sacro Cuore in Milan, working in the ERC project “LiLa: Linking Latin” and member of the executive committee of AIUCD, the Italian association of Digital Humanities.
She obtained her bachelor's and master's degrees in Humanities Computing at the University of Pisa (Italy) and her PhD in Information Technology at the University of Trento (Italy) with a thesis on the automatic detection and classification of events in historical texts.
In 2005 she moved to Trento becoming involved in Human Language Technologies projects and researches at CELCT (the former "Center for the Evaluation of Language and Communication Technologies") and then, from 2013 to 2018, she worked in the group dedicated to Digital Humanities at Fondazione Bruno Kessler.
Her research is mainly focused on text annotation, evaluation of NLP tools and on how computational methods and text analysis technologies can be applied to the treatment of cultural content.
Katrin Dennerlein is a lecturer at the University of Würzburg. She is currently working as project leader of the computational literary studies project “Emotions in Drama” in which she explores emotions with historical hermeneutic as well as computational methods. She received her PhD on the topic of narratology of space and wrote her second book (Habilitation) on the German comedy of the 17th and 18th century. Among her research interests are network analysis, mixed methods in digital humanities, AI for historical fictional texts, German drama from 1500 to 1850 and mobility in German contemporary fiction.
Thomas Schmidt is a PhD student, research assistant and lecturer at the chair for media informatics, University of Regensburg. He received his master’s degree in media informatics in 2017. He works in the computational literary studies project “Emotions in Drama” since 2020 investigating sentiment and emotions in historic German plays via computational methods. Since 2019, he is also responsible for the coordination of the master’s degree program Digital Humanities at the University of Regensburg. Among his research interests are Digital Humanities, text mining, human-computer interaction (HCI) and information behavior. In his PhD, he explores the application of computer vision in quantitative film analysis.
Bernhard Geiger (Know-Center Graz)
Christina Glatz (University of Graz)
Elisabeth Hobisch (University of Graz)
Philipp Koncar (Graz University of Technology)
Sanja Sarić (University of Graz)
Martina Scholger (University of Graz)
Yvonne Völkl (University of Graz)