Ausklasser & AI-HuSo @ FedCSIS

Insights from FedCSIS and the AI in HuSo Workshop

At the great FedCSIS conference in Warsaw, I had the opportunity to present at the “AI in Digital Humanities, Computational Social Sciences, and Economics Research” workshop. This event brought together experts and researchers in the field, providing a platform to discuss the latest advancements and challenges in AI applications within humanities and social sciences. My presentation on detecting German apprenticeship job advertisements using AI highlighted the nuanced decision-making processes in applied NLP and the potential for significant advancements in this area. I am also proud to announce that I have won the ‘Young Researcher’ award at the workshop. Thanks to all the organizers for the great experience!

Overview of the ‘Ausklasser’ Paper

The ‘Ausklasser’ paper introduces a novel NLP-based approach for classifying German apprenticeship job advertisements. The research focused on developing a distilBERT based text classification model, capable of distinguishing between apprenticeship and regular job ads. This distinction is crucial in the context of the German labor market and our work at BIBB, where apprenticeships play a significant role. The paper outlines the development process, the challenges encountered, and the parameters considered for optimal model performance. The findings provide valuable insights for researchers aiming to harness NLP for similar tasks in different languages or contexts. The paper can be accessed here.