University of Cambridge > > NLIP Seminar Series > Fighting Misinformation in Science Communication with NLP

Fighting Misinformation in Science Communication with NLP

Add to your list(s) Download to your calendar using vCal

  • UserDustin Wright (University of Copenhagen) World_link
  • ClockFriday 02 June 2023, 12:00-13:00
  • HouseComputer Lab, SS03.

If you have a question about this talk, please contact Michael Schlichtkrull.


Misinformation continues to be a problem in online discourse with tangible consequences. Misinformation related to science in particular is detrimental to people’s health and ability to make informed decisions about their behavior. But how does science misinformation manifest itself, and how can natural language processing be used to combat it at scale? In this talk, I will introduce the topic of misinformation in science communication and its relationship to general misinformation. I will then present two recent works on identifying distortions in science communication, namely on exaggeration and on general information change. Finally, I’ll discuss ongoing and future work on NLP for science communication: predicting multiple distortions in communication and analyzing the news-worthiness of scientific articles.


Dustin is a Postdoc at the University of Copenhagen researching sustainable machine learning and misinformation in science. Previously he was a PhD Fellow in the CopeNLU group where he worked on automated fact checking, automatic understanding and analysis of science communication, and domain adaptation. He received a master’s degree from University of California, San Diego, and has worked at IBM Research and Allen Institute for Artificial Intelligence on the Semantic Scholar project.

This talk is part of the NLIP Seminar Series series.

Tell a friend about this talk:

This talk is included in these lists:

Note that ex-directory lists are not shown.


© 2006-2024, University of Cambridge. Contact Us | Help and Documentation | Privacy and Publicity