After studying physics, sociology and German philology at Jena University, I joined Prof. Udo Hahn’s Group in summer 2016. Since then my work focuses on modeling emotional reactions to language on different linguistic levels (words, sentences, and texts). A distinguishing feature of our research is the close connection to psychology in terms of data sets and, in particular, formal representations of affective states. As such, my long-term goal is to push sentiment analysis away from its narrow focus on positive vs. negative feelings only but instead introducing more expressive models of emotion from psychological theory. I am also interested in applying our resulting methodologies to questions asked within the humanities and social sciences. In summer 2018, I spent three months as a visiting scholar at the University of Pennsylvania working together with Lyle Ungar. I spent summer 2019 as a research intern at Amazon Alexa where I was working on accelerating question answering models for production.
Sven Buechel, Anneke Buffone, Barry Slaff, Lyle Ungar, João Sedoc. 2018. Modeling Empathy and Distress in Reaction to News Stories. In EMNLP 2018 — Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing. Brussels, Belgium, October 31 – November 4, 2018. Pages 4758–4765. [Paper][Slides][Video][Code & Data][Preprint]
Sven Buechel and Udo Hahn. 2018. Emotion Representation Mapping for Automatic Lexicon Construction (Mostly) Performs on Human Level. In COLING 2018 — Proceedings of the 27th International Conference on Computational Linguistics. Santa Fe, New Mexico, USA, August 20-26, 2018. Pages 2892-2904. [Paper]
Sven Buechel and Udo Hahn. 2018. Word Emotion Induction for Multiple Languages as a Deep Multi-Task Learning Problem. In NAACL 2018 — Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, volume 1, long papers, pages 1907–1918 New Orleans, Louisiana, USA, June 1–6, 2018. [Paper][Video]
Sven Buechel and Udo Hahn. 2017. A Flexible Mapping Scheme for Discrete and Dimensional Emotion Representations: Evidence from Textual Stimuli. In CogSci 2017 - Proceedings of the 39th Annual Meeting of the Cognitive Science Society. London, UK, July 26-29, 2017, pages 180-185. [Paper]
Sven Buechel and Udo Hahn. 2017. EmoBank: Studying the Impact of Annotation Perspective and Representation Format on Dimensional Emotion Analysis. In EACL 2017 - Proceedings of the 15th Conference of the European Chapter of the Association for Computational Linguistics, volume 2, short papers, pages 578-585, Valencia, Spain, April 3-7, 2017. [Paper] [Poster]
Sven Buechel and Udo Hahn. 2016. Emotion analysis as a regression problem - Dimensional models and their implications on emotion representation and metrical evaluation. In ECAI 2016 - Proceedings of the 22nd European Conference on Artificial Intelligence. The Hague, The Netherlands, August 29 - September 2, 2016, pages 1114-1122. [Paper]
Emotional Enterprises? Measuring Affective Language on and by Organizations. Invited Talk at Deutsches Institut für Wirtschaftsforschung (German Institute for Economic Research, Claus Michelsen). Berlin, Germany, July 5, 2019. [Slides]
Modeling Empathy and Distress in Written Language. Invited Talk at WASSA @ NAACL 2019 (Alexandra Balahur). Minneapolis, MN, USA, June 6, 2019. [Slides]
From Sentiment to Emotion: Challenges of a More Fine-Grained Analysis of Affective Language. Invited Talk at the Institut für Maschinelle Sprachverarbeitung, Universität Stuttgart (Roman Klinger), Stuttgart, Germany, November 26, 2018. [Slides]
Emotional Enterprises? Measuring Affective Language in Companies’ External Communication. Invited Talk at the US Securities and Exchange Commission (Marco Enriquez), Washington, DC, USA, June 27, 2018. [Slides]
On Resources for Emotion Analysis Incorporating Multiple Representation Formats and Perspectives. Invited Talk at the National Research Council, Ottawa, Canada (Saif Mohammad), August 14, 2017.
|Postal Address||Fürstengraben 27
Visit us on GitHub
© 2019 JULIE Lab