Profile
Abstract
Nicolas Ruth is a research associate in the Computational Humanities Group at the Institute of Computer Science at the University of Leipzig. His research focuses on Computational Social Sciences through Active Learning and multimodal film analysis.
During his Bachelor’s studies in Digital Humanities, he placed a strong emphasis on Data Science and AI technologies. Between his Bachelor’s and Master’s degrees, he worked as a Junior Data Scientist in the Machine Learning specialist team of an IT company in Leipzig. In this role, he organized interactive training sessions on Machine Learning methods for software developers, developed ML-based solutions for the energy sector, and engaged in automated multimodal film analysis. After his time in the private sector, he continued his studies with a Master's in Data Science at the University of Leipzig.
Professional career
- since 09/2024
Research associate in the Computational Humanities Group - since 04/2022
Research assistant in the Computational Humanities Group - 11/2020 - 04/2022
Junior Data Scientist - 10/2016 - 08/2020
Freelancing photographer and videographer - 10/2016 - 07/2018
Co-Teamer of the "Landesvereinigung Kulturelle Jugendbildung Berlin e.V." - 09/2015 - 09/2016
Voluntary social year in the political sphere
Education
- 10/2021 - 08/2024
Data Science M. Sc. - 10/2017 - 04/2022
Digital Humanities B.Sc., University of Leipzig, completed - 10/2016 - 04/2017
Political science and film studies, FSU Jena, uncompleted
Nicolas Ruth focuses on the use of data science based methods to conduct research in the humanities and social sciences. In the past, he has worked intensively on exploring, supporting and expanding the psychoanalytical research approach of antisemitism as an phenomenon using data-driven natural language processing methods. The conception, creation and adaptation of machine learning models are among the essential concepts used to implement the research questions. Coming from a security perspective, he is also interested in attacks on machine learning methods and the critical examination of their use in general.
Algorithms and methods: Natural Language Processing, Psycholinguistics, Sentiment and Bias Analysis, Language Models incl. Transformers, Support Vector Machines, Multivariate Time Series Classification, Computer Vision, CNNs (object-, age- and emotion recognition), Regression Analyses, Decision tree learning, Autoencoder, Cybersecurity, Penetration Testing, Adversarial Attacks, Data Engineering, Relational Databases, SQL & NoSQL, Data Visualization, Web App Development, Apache Superset