Powered by OpenAIRE graph
Found an issue? Give us feedback
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/ ZENODOarrow_drop_down
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
ZENODO
Other literature type . 2025
License: CC BY
Data sources: ZENODO
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
ZENODO
Conference object . 2025
License: CC BY
Data sources: ZENODO
ZENODO
Article . 2025
License: CC BY
Data sources: Datacite
ZENODO
Presentation . 2025
License: CC BY
Data sources: Datacite
ZENODO
Presentation . 2025
License: CC BY
Data sources: Datacite
ZENODO
Article . 2025
License: CC BY
Data sources: Datacite
versions View all 5 versions
addClaim

Bias Detection in der historischen Textanalyse: Prompting, Perspektiven und semantische Präzision in der AI-Readiness der MHDBDB.

Authors: Hintersteiner, Julia; van Beek, Alan Lena; Zeppezauer-Wachauer, Katharina;

Bias Detection in der historischen Textanalyse: Prompting, Perspektiven und semantische Präzision in der AI-Readiness der MHDBDB.

Abstract

In diesem 90-minütigen Workshop untersuchen die Teilnehmenden anhand konkreter Beispiele aus der Mittelhochdeutschen Begriffsdatenbank (MHDBDB), wie sich Verzerrungen in historischen Textkorpora identifizieren und kritisch analysieren lassen. Die MHDBDB ist eine semantisch annotierte Forschungsinfrastruktur, die aktuell für den Einsatz in AI-gestützten Analyseverfahren vorbereitet wird. Ziel ist es, historische Daten nicht nur zugänglich, sondern auch reflektiert und bias-bewusst nutzbar zu machen. Im Zentrum des Workshops stehen zwei aufeinander aufbauende Aktivitäten: Zunächst schlüpfen die Teilnehmenden in die Rolle von Bias-Detektiv*innen und analysieren ausgewählte Begriffe aus der MHDBDB auf potenzielle Verzerrungen durch moderne Lesarten oder normdatenbasierte Kategorien. Anschließend experimentieren sie mit verschiedenen Prompting-Strategien für Large Language Models (LLMs), um zu erproben, wie sich unterschiedliche Fragestellungen auf die AI-generierten Antworten auswirken – insbesondere im Hinblick auf stereotype Reproduktionen oder historische Unschärfen. Der Workshop vermittelt praktische Kompetenzen im Umgang mit semantischen Kategorien, Prompting und Bias-Analyse und unterstützt so die Entwicklung kritischer Datenkompetenz in den Digital Humanities. Gleichzeitig leistet er einen Beitrag zur methodischen Weiterentwicklung bias-sensibler AI-Infrastrukturen für die historische Forschung.

Related Organizations
Keywords

Prompt Engineering, bias, data literacy, Historische Textanalyse, AI, prompting, Bias-Erkennung, intersectionality, FORGE2025

  • BIP!
    Impact byBIP!
    selected citations
    These citations are derived from selected sources.
    This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    0
    popularity
    This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
    Average
    influence
    This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    Average
    impulse
    This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
    Average
Powered by OpenAIRE graph
Found an issue? Give us feedback
selected citations
These citations are derived from selected sources.
This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Citations provided by BIP!
popularity
This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
BIP!Popularity provided by BIP!
influence
This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Influence provided by BIP!
impulse
This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
BIP!Impulse provided by BIP!
0
Average
Average
Average