Direkt zum Inhalt


Lebenslauf


Seit 10/2024

Wissenschaftlicher Mitarbeiter am Lehrstuhl für Medieninformatik der Universität Regensburg.

Seit 10/2024

Wissenschaftlicher Mitarbeiter am Lehrstuhl für Educational Data Science der Universität Regensburg.

01/2023 - 09/2023

Wissenschaftliche Hilfskraft am Rechenzentrum (Studienbegleitende IT-Ausbildung) der Universität Regensburg.

04/2022 - 09/2024

Wissenschaftliche Hilfskraft am Lehrstuhl für Educational Data Science der Universität Regensburg, Projekt FALKO-PV.

04/2022 - 04/2024

Studium: Master of Science (M.Sc.) Medieninformatik an der Universität Regensburg.

10/2018 - 01/2022

Studium: Bachelor of Arts (B.A.) Medieninformatik und Informationswissenschaft an der Universität Regensburg.

Forschungsinteressen


  • Natural Language Processing (NLP) / Efficient NLP
  • Data Augmentation
  • Structured Learning
  • Agents
  • Aspect-based Sentiment Analysis

Lehre


Wintersemester 2026/2027: AI Engineering / Übung Digitalisierung und digitale Gesellschaft IV

Sommersemester 2026: Multimedia/Web Engineering

Wintersemester 2025/2026: AI Engineering / Übung Digitalisierung und digitale Gesellschaft IV

Sommersemester 2025: Multimedia/Web Engineering

Wintersemester 2024/2025: Übung Digitalisierung und digitale Gesellschaft IV

Sommersemester 2023: Moderne Web-App-Entwicklung mit Javascript, Node und React

Publikationen


Hellwig, N. C., Fehle, J., Kruschwitz, U., & Wolff, C. (2026). LLM-as-an-Annotator: Training Lightweight Models with LLM-Annotated Examples for Aspect Sentiment Tuple Prediction. In Proceedings of the Fifteenth Language Resources and Evaluation Conference (LREC 2026) (pp. 7955-7972). 

Hellwig, N. C., Fehle, J., Kruschwitz, U., & Wolff, C. (2026). AnnoABSA: A Web-Based Annotation Tool for Aspect-Based Sentiment Analysis with Retrieval-Augmented Suggestions. In Proceedings of the Fifteenth Language Resources and Evaluation Conference (LREC 2026) (pp. 7985-7998). 

Fehle, J., Hellwig, N. C., Kruschwitz, U., & Wolff, C. (2026). Zero-Shot to Full-Resource: Cross-lingual Transfer Strategies for Aspect-Based Sentiment Analysis. In Proceedings of the Fifteenth Language Resources and Evaluation Conference (LREC 2026) (pp. 7999-8013).

Donhauser, N., Fehle, J., Hellwig, N. C., Weinberger, M., Kruschwitz, U., & Wolff, C. (2026). Annotation Quality in Aspect-Based Sentiment Analysis: A Case Study Comparing Experts, Students, Crowdworkers, and Large Language Models. In Proceedings of the Fourth Workshop on the Role of Resources in the Age of Large Language Models (RESOURCEFUL 2026) (pp. 73-88). 

Hellwig, N. C., Fehle, J., Kruschwitz, U., & Wolff, C. (2026). nchellwig at SemEval-2026 Task 3: Self-Consistent Structured Generation (SCSG) for Dimensional Aspect-Based Sentiment Analysis using Large Language Models. In Proceedings of the 20th International Workshop on Semantic Evaluation (SemEval-2026) (pp. 37-47). 

Schmerle, M., & Hellwig, N. C. (2026). schmerle at SemEval-2026 Task 4: Exploring Large Language Model Prompting Strategies for Low-Resource Narrative Similarity Detection. In Proceedings of the 20th International Workshop on Semantic Evaluation (SemEval-2026) (pp. 2046-2056). 

Hellwig, N. C., Fehle, J., Kruschwitz, U., & Wolff, C. (2025, August). Do we still need human annotators? prompting large language models for aspect sentiment quad prediction. In Proceedings of the 1st Joint Workshop on Large Language Models and Structure Modeling (XLLM 2025) (pp. 153-172).

Fehle, J., Donhauser, N., Kruschwitz, U., Hellwig, N. C., & Wolff, C. (2025, September). German Aspect-based Sentiment Analysis in the Wild: B2B Dataset Creation and Cross-Domain Evaluation. In Proceedings of the 21st Conference on Natural Language Processing (KONVENS 2025): Long and Short Papers (pp. 213-227).

Hellwig, N. C., Fehle, J., & Wolff, C. (2025). Exploring large language models for the generation of synthetic training samples for aspect-based sentiment analysis in low-resource settings. Expert Systems with Applications, 261, 125514. Elsevier.

Hellwig, N. C., Fehle, J., Bink, M., Schmidt, T., & Wolff, C. (2024). Exploring Twitter discourse with BERTopic: Topic modeling of tweets related to the major German parties during the 2021 German federal election. International Journal of Speech Technology, 1–21. Springer.

Hellwig, N. C., Fehle, J., Bink, M., & Wolff, C. (2024, September). GERestaurant: A German Dataset of Annotated Restaurant Reviews for Aspect-Based Sentiment Analysis. In Proceedings of the 20th Conference on Natural Language Processing (KONVENS 2024) (pp. 123-133).

Boehner, S., Fuchs, T., Hellwig, N. C., Hellwig, A., Fischer, R., Schmidt, D., & Hellwig, D. (2024). Validierung einer vollautomatischen Analyse-Pipeline für die Artificial-Intelligence (AI)-unterstützte Quantifizierung von PET/CT-Bilddaten in einem Medizinischen Datenintegrationszentrum. Nuklearmedizin-NuclearMedicine, 63(02), V62.

Hellwig, N. C., Bink, M., Schmidt, T., Fehle, J., & Wolff, C. (2023, December). Transformer-Based Analysis of Sentiment Towards German Political Parties on Twitter During the 2021 Election Year. In Proceedings of the 6th International Conference on Natural Language and Speech Processing (ICNLSP 2023) (pp. 84-98).

nach oben