Preventing the spread of misinformation

Peter Ebert Christensen (Ph.D. Student)

As a part of doing research communication between different partners is key, both when working with teams and writing papers. Research into what people are actually saying, e.g. their narratives surrounding a topic, despite the unknown degree of the truth of it. Traditionally the focus has been on fact checking within NLP and not the narratives and it would be amazing to explore this area to gain insight into the underlying way human narratives form and why they do so. Initially a formulation of the narratives will have to be developed, data gathered with humans in the loop after which we will start to investigate how well current models can find our latent narratives. Other areas of interest include abstract summarisation, topic modelling, online social discourse analysis, sentiment analysis and crowdsourcing which will be investigated to determine if and how these models can help discover narratives and grow the database.

Primary Host:	Serge Belongie (University of Copenhagen & Cornell University)
Exchange Host:	Iryna Gurevych (Technical University of Darmstadt)
PhD Duration:	01 September 2022 - 31 August 2025
Exchange Duration:	01 April 2023 - 30 September 2023 - Ongoing