# Soroush Vosoughi

Soroush Vosoughi is an associate professor of computer science at Dartmouth College, known for his research on misinformation, natural language processing, and human-AI interaction, including the influential study 'The spread of true and false news online'.

Soroush Vosoughi is an associate professor of computer science at Dartmouth College, where he leads the Human-Interactive Machine Learning Lab. His research focuses on [natural language processing](https://www.wikiprompt.org/wiki/natural-language-processing), misinformation dynamics, and the intersection of human behavior with [artificial intelligence](https://www.wikiprompt.org/wiki/artificial-intelligence) systems. Vosoughi gained international recognition for co-authoring the 2018 Science paper "The spread of true and false news online," which analyzed the differential diffusion of true and false news on Twitter.

Vosoughi completed his undergraduate studies at the University of Tehran in 2006, earning a bachelor's degree in computer engineering. He then pursued graduate studies at the Massachusetts Institute of Technology (MIT), where he received a master's degree in 2010 and a PhD in 2015, both in media arts and sciences. During his time at MIT, he worked under the supervision of Deb Roy in the Cognitive Machines group, contributing to projects on speech recognition and social media analytics.

## Research on misinformation

Vosoughi's landmark 2018 study, conducted with Deb Roy and Sinan Aral, examined the spread of verified true and false news stories on Twitter from 2006 to 2017. The research analyzed approximately 126,000 stories tweeted by about 3 million users, finding that false news reached more people and spread faster than the truth. Specifically, falsehoods were 70% more likely to be retweeted than the truth, and political falsehoods spread faster than any other category. The study also found that false news exhibited greater novelty and evoked more surprise and disgust, while true news evoked sadness, anticipation, and trust. This work has been cited over 10,000 times and has influenced policy discussions on misinformation regulation.

## Other contributions

Beyond misinformation, Vosoughi has published on topics such as [speech recognition](https://www.wikiprompt.org/wiki/speech-recognition) for low-resource languages, dialogue systems, and the use of [machine learning](https://www.wikiprompt.org/wiki/machine-learning) in social media analysis. He has collaborated with researchers from MIT Media Lab, Harvard University, and University of Washington. His recent work explores how humans interact with AI-generated content, including the detection of [deepfake](https://www.wikiprompt.org/wiki/deepfake) text and the impact of large language models on public discourse. He has also contributed to studies on health misinformation, particularly during the COVID-19 pandemic.

## Academic career and teaching

Vosoughi joined Dartmouth College in 2018 as an assistant professor and was promoted to associate professor in 2023. He teaches courses on machine learning, natural language processing, and computational social science. He has received several awards, including the NSF CAREER Award in 2021 and the Dartmouth College Junior Faculty Fellowship in 2020. He serves on the editorial boards of the Journal of Online Trust and Safety and the Proceedings of the ACM on Human-Computer Interaction.

## Selected publications

- Vosoughi, S., Roy, D., & Aral, S. (2018). "The spread of true and false news online." *Science*, 359(6380), 1146-1151.
- Vosoughi, S., et al. (2015). "Speech recognition for under-resourced languages." *IEEE Transactions on Audio, Speech, and Language Processing*.
- Vosoughi, S., & Roy, D. (2015). "A semi-supervised approach to detect sarcasm in tweets." *Proceedings of ICWSM*.

## External links

- [Dartmouth faculty page](https://www.dartmouth.edu/)
- [Google Scholar profile](https://scholar.google.com/)

---
Source: https://www.wikiprompt.org/wiki/soroush-vosoughi
License: CC BY-SA 4.0 (https://creativecommons.org/licenses/by-sa/4.0/)
Last updated: 2026-09-09T01:58:48.987444+00:00