Michela Vignoli

Porträt Michela Vignoli




Michela Vignoli is PhD candidate at the University of Vienna, and data scientist at AIT Austrian Institute of Technology. During her research career at AIT, she contributed to various DH and open science projects as well as to related publications. In 2020 Michela started her specialisation in applied Artificial Intelligence (AI) and Machine Learning (ML) for supporting reasoning and argumentation in social sciences and the humanities. In 2022 she started her PhD in Digital Humanities at the University of Vienna.

Current research project: Ottoman Nature in Travelogues (ONiT) and AI-Driven Text-Image Relation Analysis in Historical Sources
The goal of this doctorate is to develop an interdisciplinary methodological framework for AI-driven analysis of text-image relations in large, digitized historical data corpora. The focus is to discuss the added value as well as the limitations of AI-supported methods in historical research. Moreover, this dissertation will explore to what extent research questions related to the history of knowledge, which are predominantly qualitative in nature, can be supported by computational (i.e., quantitative) approaches.
The method is being developed on the example of a heterogeneous corpus of travelogues from 1501-1850 in multiple languages, which contain western representations of Ottoman “nature” in text and image. This work is funded as part of the FWF project no. P 35245-G ONiT: Ottoman Nature in Travelogues (led by the Austrian Academy of Science, with AIT Austrian Institute of Technology as a consortium partner). ONiT studies representations of nature of the Ottoman Empire in historical travel literature held by the Austrian National Library. The PhD project develops a methodological and technical framework for its automated analysis.


  • together with D. Gruber, R. Simon, Revolution or Evolution? AI-Driven Image Classification of Historical Prints. DH 2023 Collaboration as Opportunity (under review)
  • together with J. Rörden, D. Wasserbacher, S. Kimpeler, An Exploration of the Potential of Machine Learning Tools for Media Analysis to Support Sense-Making Processes in Foresight. Frontiers in Communications, 7, 2022. DOI: http://dx.doi.org/ 10.3389/fcomm.2022.750614
  • together with J. Rörden, Why We Need Open Science Communication Experts. Mitteilungen der Vereinigung Österreichischer Bibliothekarinnen und Bibliothekare 72(2), 2019. DOI: https://doi.org/10.31263/voebm.v72i2.3049