Explaining item-nonresponse in open questions with requests for voice responses. Salvatore, C., & Höhne, J. K. (2025, Juni). Explaining item-nonresponse in open questions with requests for voice responses. Vortrag auf dem Workshop Mobile Apps and Sensors in Surveys (MASS), London School of Economics (LSE), UK.
|
Mobile device tracking: Explaining discrepancies between survey self-reports and digitally tracked behavior. Claaßen, J., Bosch, O., & Höhne, J. K. (2025, Juni). Mobile device tracking: Explaining discrepancies between survey self-reports and digitally tracked behavior. Vortrag auf dem Workshop Mobile Apps and Sensors in Surveys (MASS), London School of Economics (LSE), UK.
|
Comparing LLM-driven bots with answers from a Facebook survey. Claaßen, J., & Höhne, J. K. (2025, Mai). Comparing LLM-driven bots with answers from a Facebook survey. Poster auf dem Workshop Computational Social Science: AI and Society – Exploring Inequality in the Digital Age, University of Mannheim.
|
Meet-the-data: EUROSTUDENT – Daten zur Hochschulbildung in Europa. Hauschildt, K., & Daniel, A. (2025, Mai). Meet-the-data: EUROSTUDENT – Daten zur Hochschulbildung in Europa. Vortrag im Rahmen der Meet-the-Data-Veranstaltungsreihen 2024/2025, Verbund Forschungsdaten Bildung (VerbundFDB).
|
Daten sicher teilen - Landkarte der Möglichkeiten. Buck, D., Hoffstätter, U., Beck, K., Siegers, P., Linne, M., & Schlücker, F. (2025, Mai). Workshop Daten sicher teilen - Landkarte der Möglichkeiten.
|
Datenüberlassung an ein FDZ oder selbst eines gründen? Aufgaben und Strukturen eines FDZ. Siegers, P., & Buck, D. (2025, Mai). Datenüberlassung an ein FDZ oder selbst eines gründen? Aufgaben und Strukturen eines FDZ. Vortrag auf dem Workshop Daten sicher teilen - Landkarte der Möglichkeiten.
|
AutoML meets hugging face: Domain-aware pretrained model selection for text classification. Safikhani, P. (2025, April/Mai). AutoML meets hugging face: Domain-aware pretrained model selection for text classification. Poster auf der Konferenz 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies, Albuquerque, USA.
Abstract
The effectiveness of embedding methods is crucial for optimizing text classification performance in Automated Machine Learning (AutoML). However, selecting the most suitable pre-trained model for a given task remains challenging. This study introduces the Corpus-Driven Domain Mapping (CDDM) pipeline, which utilizes a domain-annotated corpus of pre-fine-tuned models from the Hugging Face Model Hub to improve model selection. Integrating these models into AutoML systems significantly boosts classification performance across multiple datasets compared to baseline methods. Despite some domain recognition inaccuracies, results demonstrate CDDM’s potential to enhance model selection, streamline AutoML workflows, and reduce computational costs.
|
Bots in web survey interviews: A showcase. Höhne, J. K., Claaßen, J., Shahania, S., & Broneske, D. (2025, März/April). Bots in web survey interviews: A showcase. Vortrag im Rahmen der General Online Research (GOR) Conference, Berlin.
|
Bots in web surveys: Predicting robotic language in open narrative answers. Claaßen, J., Höhne, J. K., Bach, R., & Haensch, A.-C. (2025, März/April). Bots in web surveys: Predicting robotic language in open narrative answers. Vortrag im Rahmen der General Online Research (GOR) Conference, Berlin.
|
Static and dynamic contextual embedding for AutoML in text classification tasks. Safikhani, P. (2025, März). Static and dynamic contextual embedding for AutoML in text classification tasks. Vortrag auf der Konferenz International Conference on Natural Language Processing (ICNLP 2025), Guangzhou, China.
|
Jenseits von Anti-Elitismus und Kulturkämpfen: Wie vermeintliche Sorgen der Bürger:innen den Populismus der AfD auf TikTok prägen. Meyer, H., Niemann-Lenz, J., Rodeck, L., & Revers, M. (2025, März). Jenseits von Anti-Elitismus und Kulturkämpfen: Wie vermeintliche Sorgen der Bürger:innen den Populismus der AfD auf TikTok prägen. Vortrag auf dem Workshop DGPuK Pre-Conference: Erosion demokratischer Werte?, Berlin, Deutschland.
|
VerbCraft: Morphologically-aware Armenian text generation using LLMs in low-resource settings. Avetisyan, H. (2025, März). VerbCraft: Morphologically-aware Armenian text generation using LLMs in low-resource settings. Poster auf der Konferenz The Joint 25th Nordic Conference on Computational Linguistics and 11th Baltic Conference on Human Language Technologies (NoDaLiDa/Baltic-HLT 2025), Tallinn, Estonia.
|
How does smartphone participation in probability-based web surveys differ across Europe? Höhne, J. K., Claaßen, J., Gummer, T., & Rettig, T. (2025, Februar). How does smartphone participation in probability-based web surveys differ across Europe? Vortrag im Rahmen der 7th Conference of Current Innovations in Probability-based Household Internet Panel Research (CIPHER), Washington, D.C., USA.
|
Synthesizing LGBTQ-related attitudes: Comparing LLM-driven bots and survey respondents. Claaßen, J., & Höhne, J. K. (2025, Februar). Synthesizing LGBTQ-related attitudes: Comparing LLM-driven bots and survey respondents. Poster auf dem Workshop Novel Data Sources, New Methods, and Computational Approaches for Understanding Discrimination and Bias, MZES, Mannheim.
|
NLP beyond boundaries: Integrating high-resource foundations with low-resource innovations. Avetisyan, H. (2025, Februar). NLP beyond boundaries: Integrating high-resource foundations with low-resource innovations. Vortrag auf dem Kolloquium Doktorandentag at Otto von Guericke University Magdeburg, Faculty of Computer Science, Magdeburg, Germany.
|
