معرفی
Gabriella Lapesa is a Junior Professor for Responsible Data Science and Machine Learning at Heinrich-Heine University Düsseldorf and leads the Data Science Methods team in the Department of Computational Social Science at GESIS Cologne. She is also the leader of the BMBF-funded group E-DELIB at the University of Stuttgart (until December 2024). Her work bridges computational linguistics with social science applications, focusing on NLP methods in interdisciplinary contexts.
Her research interests span computational linguistics and Natural Language Processing applications in social and political sciences. She specializes in supporting decision-making in forums with NLP and capturing the dynamics of political debates in newspaper reports. Additional research domains include applying NLP methods to cognitive modeling and linguistics, particularly prediction of speakers' behavior in psycholinguistic experiments and lexical semantics.
Lapesa's recent publications demonstrate a strong focus on argumentation mining, political discourse analysis, and moderation in online discussions. Her work shows a trend toward integrating multiple information sources for argument analysis, addressing challenges in modeling subjective phenomena, and developing methods for low-resource NLP scenarios. She has made significant contributions to understanding socio-cultural differences in argumentation and developing NLP tools for political communication analysis.
- BMBF-funded group E-DELIB (Powering up E-DELIBeration: towards NLP-supported moderation)
Lapesa leads the Data Science Methods team at GESIS, which contributes to the GESIS infrastructure for Computational Social Science research by developing novel methods. The team focuses on fostering interaction between NLP and Social Science, developing solutions that integrate multiple information sources and address recent challenges in NLP such as modeling subjective phenomena, low-resource scenarios, and identifying/mitigating bias. The team tackles research questions at the interface between computational argumentation and computational social science, targeting political communication from a broad perspective involving different types of actors and discourse contexts.
