Researcher biography
Dr. Martin Schweinberger is Associate Professor and Lab Director in the AcqVA-Aurora Center at the Arctic University of Norway in Tromsø. In addition, Martin holds a part-time appointment as Postdoctoral Research Fellow in Language Technology at the University of Queensland, Australia where he has been establishing the Language Technology and Data Analysis Laboratory (LADAL).
Regarding his research focus, Martin is a language data scientist with a PhD in English linguistics who specializes in quantitative statistical modeling and computational analyses of language data as well as linguistic data visualization and natural language processing.
In his research, Martin is particularly interested in understanding mechanisms of language change as well as determinants of language use and linguistic variability. Martin is an avid proponent of improving computational support infrastructures for humanities research, building bridges between data science and the humanities, and promoting sustainable research practices and data management.
At the 2020 webinar forum What can the humanities tell us about COVID-19?, Martin Schweinberger and Michael Haugh explored different phases in responses to the Covid-19 situation in Australia.
For this project, Schweinberger and Haugh used a text-mining approach to ascertain different phases in responses to the Coronavirus (COVID-19) situation amongst Australian Twitter users. Schweinberger and Haugh analysed the data through a linguistic lens to find what topics characterize these phases, which concepts were particularly prominent in each phase and how the emotional response to different issues related to COVID-19 changed during the unfolding of the COVID-19 situation. It’s projects such as these that illuminate Schweinberger’s interest in combining computation-heavy machine learning methods with a traditional humanities, text-oriented approach to arrive at a more detailed understanding of the evolution and stratification in discourse patterns.
Using innovative statistical modelling and data science principles, Martin aims to support language teachers and learners by unearthing which difficulties language background specific problems learners face and how these problems can be best addressed in language teaching environments. Furthermore, Martin is particularly interested in understanding how social, regional, and cognitive factors impact language use and language-related identity construction.