GESIS Leibniz Institute for the Social Sciences: Go to homepage

Human Information Interaction & Information Retrieval

Research in the field of human information interaction and information retrieval is concerned with how people search for, find, and use information – and how they can be better supported in doing so. On the one hand, this includes the targeted search for scientific content such as data sets, machine learning models, or publications. On the other hand, it also examines how people find information and behave on the web, for example on social media platforms.

Important research questions include: How can the information needs of users be better understood? How can search and interaction behavior be classified automatically, e.g., with the help of machine learning? Which methods can optimize ranking and recommendation systems and make them fair? Which methods can be used to open up unstructured documents such as publications for searches? How can trust in AI models and their explainability be improved?

Our research in this area combines approaches from information retrieval, machine learning, information extraction/NLP, and human information interaction in order to provide innovative methods, infrastructures, or data offerings. 

Research Output

  • Linzbach, Stephan, Dimitar Dimitrov, Laura Kallmeyer, Kilian Evang, Hajira Jabeen, and Stefan Dietze. 2024. "Dissecting Paraphrases: The Impact of Prompt Syntax and supplementary Information on Knowledge Retrieval from Pretrained Language Models." In Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics (NAACL2024).  Mexico City, Mexico: Association for Computational Linguistics, ACL2024. doi: 10.48550/arXiv.2404.01992.
  • Otto, Wolfgang, Matthäus Zloch, Lu Gan, Saurav Karmakar, and Stefan Dietze. 2023. "GSAP-NER: A Novel Task, Corpus, and Baseline for Scholarly Entity Extraction Focused on Machine Learning Models and Datasets." In Findings of the Association for Computational Linguistics: EMNLP 2023, 8166-76, Singapore: Association for Computational Linguistics. doi: 10.48550/arXiv.2311.09860.
  • Papenmeier, Andrea, Dagmar Kern, Gwenn Englebienne, and Christin Seifert. 2022. "It's Complicated: The Relationship between User Trust, Model Accuracy and Explanations in AI." ACM transactions on computer human interaction 29 (4): 35. doi: 10.1145/3495013
  • Schmüser, Juliane, Harshini Sri Ramulu, Noah Wöhler, Christian Stransky, Felix Bensmann, Dimitar Dimitrov, Sebastian Schellhammer, Dominik Wermke, Stefan Dietze, Yasemin Acar, and Sascha Fahl. 2024. "Analyzing Security and Privacy Advice During the 2022 Russian Invasion of Ukraine on Twitter." In CHI '24: Proceedings of the CHI Conference on Human Factors in Computing Systems, ed. Florian Floyd Mueller, Penny Kyburz, Julie R. Williamson, Corina Sas, Max L. Wilson, Phoebe Toups Dugas, and Irina Shklovski, 574, 1-16. New York: Association for Computing Machinery. doi: 10.1145/3613904.3642826.
  • Yu, Zehui, Lukas Otto, Dennis Assenmacher, and Claudia Wagner. 2024. "A Systematic Review of the Effects of AI-Assisted Moderation on Individuals and Groups." Human-Machine Communication 9: 167-88. doi: 10.30658/hmc.9.10.