Intro

Since 2023, I have been a postdoctoral researcher at the Copenhagen Research Center for Biological and Precision Psychiatry and the Novo Nordisk Foundation Center for Metabolic Research. I am currently working on the PRECIS-EHR project, funded by The Lundbeck Foundation and the Mental Health Services in the Capitol Region of Denmark. Within the PRECIS-EHR project, I am developing NLP methods for analysing clinical notes, at a large scale, and developing Large Language Models for predicting psychiatric outcomes.

My main research area is Natural Language Processing (NLP), with a focus on evaluation methods and recognising biases of NLP models. I hold a PhD in Social Data Science from the University of Copenhagen (2023). My PhD thesis was on "Biases in Natural Language Processing" and consisted of highly interdisciplinary studies conducted at the Copenhagen Center for Social Data Science (SODAS) and the CoAStaL NLP group.

In my spare time I like to play Dungeons & Dragons and board games, drink lots of coffee, and pet cats when the opportunity arises.

CV

Work Experience

• Apr. 2023 - Now Postdoc at Copenhagen Research Centre for Biological and Precision Psychiatry and the Novo Nordisk Foundation Center for Basic Metabolic Research.
• Jan. 2023 - Mar. 2023 Research Assistent at Copenhagen Center for Social Data Science, University of Copenhagen.
• Dec. 2019 - Dec. 2022 PhD Candidate at Copenhagen Center for Social Data Science and CoAStaL NLP, University of Copenhagen.
• Feb. 2019 - Nov. 2019 Student Assistant at Copenhagen Center for Social Data Science, University of Copenhagen.
• Sep. 2018 - Jan. 2019 Teaching Assistant at the Department of Nordic Studies and Linguistics (NorS), University of Copenhagen
• Dec. 2015 - Jul. 2017 Student Assistent at The Initiative for Science, Society and Policy (ISSP) and The Danish Nudging Network, Roskilde University.

Education

• Dec. 2019 - Mar. 2023 PhD in Social Data Science, University of Copenhagen.
• 2017 - 2019 MSc in IT and Cognition, University of Copenhagen.
• 2017 - 2017 Behavioural Science and Game Theory (summer courses), The London School of Economics and Political Science.
• 2014 - 2017 BSc in Informatics and Social Studies, Humanistic-Technology, Roskilde University.

Teaching Experience

• 2020 - 2021 Introduction to Social Data Science (Master’s level course), University of Copenhagen.
  Lecturer on the subject “Text as Data” in two consecutive years. The course targeted students with little or no experience with Python and my lectures offered a practical introduction to pre- processing text data and performing a simple text classification task, taught with a mixture of exercises, recorded video material, live lecture and office hours. My video material is publicly available on YouTube.
• 2020 - 2021 Student supervision, University of Copenhagen.
  Co-supervisor for two MSc theses and supervisor for two independent projects, all of students from the Department of Economics applying NLP methods to economic research questions.
• 2021 Advanced Social Data Science II (Master’s level course), University of Copenhagen.
  Teaching Assistant. The course taught advanced, practical Python Machine/Deep Learning and Topic Modelling with, especially, images and text data.
• 2020 Social Data Science: Text as Data and Deep Learning (Master’s level course), University of Copenhagen.
  Teaching Assistant. The course introduced students to Deep Learning with theoretical foundations and with practical Keras exercises. The course had an emphasis on text data but included exercises with images as well.
• 2018 - 2019 Scientific Programming (Master’s level course), University of Copenhagen.
  Teaching Assistant. The course offered a practical introduction to Machine Learning and data analysis with Python, using both structured and unstructured data.
• 2019 Humanistiske Designmetoder II (Bachelor’s level course), Roskilde University.
  Guest Lecturer on the subject “Nudging” and research design methods relevant for nudging experiments.

Talks and outreach

Publications

Terne Sasha Thorn Jakobsen, Enric Cristobal Coppulo, Simon Rasmussen, Michael Eriksen Benros. Forthcoming. PsyRoBERTa: A Large Language Model for Predicting Psychiatric Outcomes from Danish Clinical Notes.

Terne Sasha Thorn Jakobsen, Andreas Bjerre-Nielsen and Robert Böhm. Forthcoming. Reducing annotator bias by belief elicitation.

Terne Sasha Thorn Jakobsen, Laura Cabello, and Anders Søgaard. 2023. Being Right for Whose Right Reasons?. In Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1033–1054, Toronto, Canada. Association for Computational Linguistics.

Terne Sasha Thorn Jakobsen and Anna Rogers. 2022. What Factors Should Paper-Reviewer Assignments Rely On? Community Perspectives on Issues and Ideals in Conference Peer-Review. In Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pages 4810–4823, Seattle, United States. Association for Computational Linguistics.

Terne Sasha Thorn Jakobsen, Maria Barrett, Anders Søgaard, and David Dreyer Lassen. 2022. The Sensitivity of Annotator Bias to Task Definitions in Argument Mining. In Proceedings of the 16th Linguistic Annotation Workshop (LAW-XVI) within LREC2022, pages 44–61, Marseille, France. European Language Resources Association.

Terne Sasha Thorn Jakobsen, Maria Barrett, and Anders Søgaard. 2021. Spurious Correlations in Cross-Topic Argument Mining. In Proceedings of *SEM 2021: The Tenth Joint Conference on Lexical and Computational Semantics, pages 263–277, Online. Association for Computational Linguistics.

About

Lorem ipsum dolor sit amet, consectetur et adipiscing elit. Praesent eleifend dignissim arcu, at eleifend sapien imperdiet ac. Aliquam erat volutpat. Praesent urna nisi, fringila lorem et vehicula lacinia quam. Integer sollicitudin mauris nec lorem luctus ultrices. Aliquam libero et malesuada fames ac ante ipsum primis in faucibus. Cras viverra ligula sit amet ex mollis mattis lorem ipsum dolor sit amet.

Contact

Want to talk to me? You are welcome to send me an e-mail or a message on LinkedIn using the links below!

• Mail
• Linkedin
• Twitter
• GitHub
• Youtube

Elements

i = 0;

while (!deck.isInOrder()) {
    print 'Iteration ' + i;
    deck.shuffle();
    i++;
}

print 'It took ' + i + ' iterations to sort the deck.';