The Department of History is hosting a Speaker Series, featuring Professor Mikko Tolonen from the University of Helsinki.
This talk aims to envision how the use of machine learning and data-driven approaches can become an everyday practice for historians in the not-too-distant future. Drawing from the lessons learned from a decade of collaborative work at an interdisciplinary Helsinki Computational History Group (COMHIS), the talk will discuss the group’s research strategy and some of their recent studies of the Enlightenment. COMHIS has worked to harmonize and integrate metadata and full text sources, including the English Short Title Catalogue (ESTC) and Eighteenth Century Collections Online (ECCO). The talk will introduce the concept of bibliographic data science and use it to examine the representativeness and biases in ECCO. Of the many down-stream use cases, the talk will focus on eighteenth-century reception studies and networks of publishing in the Scottish Enlightenment. The talk will end with a demonstration of the possibilities of using unstructured ECCO data and large language model (BERT) for clustering eighteenth-century subject topics that feeds back to the ESTC metadata creating a virtuous circle in the research use of the available data.
Mikko Tolonen PhD is Associate Professor in Digital Humanities at the Faculty of Arts at the University of Helsinki. His background is in intellectual history, and he is the PI of Helsinki Computational History Group (COMHIS). His main research focus is on an integrated study of public discourse and knowledge production that combines metadata from library catalogues as well as full-text archives of books, newspapers and periodicals in early modern Europe. Tolonen works also in other areas of Enlightenment studies. Currently he is leading two Academy of Finland projects: Rise of Commercial Society and Eighteenth-Century Publishing (RiCEP); and Detection of Historical Discourses with High-Performance Computing (HPC-HD).
All are Welcome!