ºÃÉ«ÏÈÉúTV

Member of the Technical Staff at Microsoft AI

Narrative Networks: Investigating Patterns of Influence and Propaganda across International News Outlets

 Abstract:

Misinformation, disinformation, and propaganda undermine trust in institutions, spread falsehoods, and can incite violence. Despite their significant impact, the research community largely lacks automated and programmatic approaches for tracking misinformation across different online platforms.

In this talk, I demonstrate how recent advancements in transformer-based models can help combat the global proliferation of misinformation. Specifically, I propose and develop a system leveraging these models to help scalably identify, track, and analyze the spread of misinformation across thousands of international news websites. By employing novel multilingual Matryoshka embeddings and hierarchical level-wise clustering, my proposed system identifies individual news stories, topics, and overarching themes across news outlets. Utilizing multilingual stance detection, natural language inference, and network analysis, my system further assesses biases and factual inconsistencies in news articles, enabling the identification of websites and networks that disseminate propaganda or misinformation.

My approach illustrates how narrative-based tracking and deep natural language understanding can track multilingual and international news stories, support reporting and fact-checking, and ultimately help mitigate the global spread of misinformation, disinformation, and propaganda.

Link to papers:
- Hierarchical Level-Wise News Article Clustering via Multilingual Matryoshka Embeddings: 

- Tracking the Takes and Trajectories of English-Language News Narratives across Trustworthy and Worrisome Websites: 

 Bio:

Hans is a Member of Technical Staff at Microsoft AI. Hans is broadly interested in disinformation, networks, and natural language processing. Hans was formerly a Computer Science Ph.D. candidate at Stanford University researching in the Empirical Security Research Group and supported by the Meta PhD Research Fellowship, the National Science Foundation Graduate Research Fellowship and the Stanford University EDGE Fellowship. Hans completed two Masters’ degrees in Computer Science and in Statistics with the Daniel M. Sachs Scholarship at the University of Oxford. Hans completed my undergraduate degree in Electrical Engineering at Princeton University.

Please register in advance, you will then receive a confirmation email containing zoom line information about joining the seminar.  You do not need a zoom account to attend or register.

 The IDeaS Seminar series are held during Spring and Fall semesters.

If you have suggestions for speakers, .

 If you have questions about upcoming seminars, please use the contact us link below.

**Unless noted all seminars will be held virtually via Zoom. Additional talk details and registration links will be posted online prior to seminar dates. Email centerforideas@andrew.cmu.edu to be added to the mailing list.

Upcoming Seminars: 

IDeaS Spring 2026 Seminar Series:

Tuesday, April 14, 2026

Associate Professor of Law at Forham Law School

Tuesday, April 28, 2026

 Litigation Director, Knight Institute

Additional talk details and registration links will be posted online prior to seminar dates.

Past Seminars Presenters