Kilian Theil
Researcher
B6, 26, Room C1.05
E-mail: kilian (at) informatik.uni-mannheim.de
Focus group: Artificial intelligence
Research Interests
- Natural Language Processing in behavioral economics
- Linguistic uncertainty detection in financial disclosures
- Risk explanation/
prediction from text
- Ethical implications of smart cities
- Agent-based traffic simulations
Working Papers
- Theil, Kilian; Hovy, Dirk; Stuckenschmidt, Heiner: “Top-Down Influence? Predicting CEO Personality and Risk Impact from Speech Transcripts.” arXiv link.
- Theil, Kilian; Daube, Jens; Stuckenschmidt, Heiner: “Causal Effects of Linguistic Uncertainty on Risk Perception and Investment Behavior.” SSRN link.
Publications
- Theil, K., Hovy, D. and Stuckenschmidt, H. (2023). Top-down influence? Predicting CEO personality and risk impact from speech transcripts. In , Proceedings of the seventeenth International AAAI Conference on web and social media : June 5th – 8th 2023, Limassol, Cyprus (S. 832–841). International AAAI Conference on Web and Social Media, AAAI Press: Palo Alto, Calif..
- Kappenberger, J., Theil, K. and Stuckenschmidt, H. (2022). Evaluating the impact of AI-based priced parking with social simulation. In , Social Informatics: 13th International Conference, SocInfo 2022, Glasgow, UK, October 19–21, 2022, proceedings (S. 54–75). Lecture Notes in Computer Science, Springer: Berlin [u.a.].
- Theil, C. K. and Stuckenschmidt, H. (2020). Predicting modality in financial dialogue. In , FNP-FNS 2020 : Proceedings of the 1st Joint Workshop on Financial Narrative Processing and MultiLing Financial Summarisation, December 2020, Barcelona, Spain (Online) (S. 226–234). ACL Anthology, Association for Computational Linguistics: Stroudsburg, PA.
- Theil, C. K., Štajner, S. and Stuckenschmidt, H. (2020). Explaining financial uncertainty through specialized word embeddings.
ACM/
IMS Transactions on Data Science : TDS, 1, Article 6, 1–19.
- Gerdon, F., Theil, C. K., Kern, C., Bach, R. L., Kreuter, F., Stuckenschmidt, H. and Eckert, K. (2020). Exploring impacts of artificial intelligence on urban societies with social simulations. 40. Kongress der Deutschen Gesellschaft für Soziologie, Online.
Review Activities
- EPJ Data Science
- EMNLP 2021 (computational social science track)
- ACL-IJCNLP 2021 (computational social science track)
Teaching
- AI in Industry (spring 2022, M.Sc.)
- Team Project “Social Simulation” (spring 2021, M.Sc.)
- dataakademie: “Natural Language Processing” (fall 2020, practitioners)
- CS 704 Social Simulation Seminar (spring 2020, M.Sc.)
- Team Project “Smart City” (spring 2019, M.Sc.)
- IPSDS: SURV704 Computer-Based Content Analysis II (spring 2019 & 2020)
- IPSDS: SURV703 Computer-Based Content Analysis I (fall 2018 & 2019)
Students
- Jonathan Baumert (2022, M.Sc.): Measuring Corporate Alignment with the Sustainable Development Goals
- Jakob Gutmann (2021, M.Sc.): Modelling Dynamic Pricing Schemes for Parking in Inner Cities
- Paul Exner (2021, B.Sc.): Simulating Socio-Economic Effects of Parking Violation Detection
- Jens Daube (2020, M.Sc.): Experimental Evaluation of Uncertainty Perception in Financial Disclosures
- Eni Papuciu (2019, M.Sc.): Detecting Linguistic Uncertainty in Finance and Measuring Its Perception
Supplementary Material
- Code and data of our 2020 COLING FNP paper “Predicting Modality in Financial Dialogue”
- Code and data of our 2020 ACM-TDS paper “Explaining Financial Uncertainty Through Specialized Word Embeddings”
- Code, data and embedding models of our 2019 IJCAI paper “PRoFET: Predicting the Risk of Firms from Event Transcripts”
- Appendix and embedding model of our 2018 ACL ECONLP paper “Word Embeddings-Based Uncertainty Detection in Financial Disclosures”
- Dataset of our 2017 CICLing paper; sentences and labels (“c” = certain, “u” = uncertain) are comma-separated