Soroush Vosoughi

|Assistant Professor
Academic Appointments
  • Assistant Professor of Computer Science

  • Faculty Member, Institute for Security, Technology and Society

Connect with Us

I lead the minds, machines, and society group at Dartmouth. My main interests lie at the intersection of <b>natural language processing, machine learning, network science, and social media analytics. Our group is especially interested in computational social science, developing computational tools (with a large focus on NLP tools) to study social systems and issues such as political polarization, propaganda, bias, rumors, mental health, and hate speech. The methods we study cover various technical topics, from style transfer and psycho- and socio-linguistic models to few-shot learning, prompt-based methods, and data augmentation. We are also particularly interested in studying the bias, morality, and interpretability of foundation language models that have revolutionized NLP and that our research relies on. I am a member of the machine learning lab, the Institute for Security, Technology, and Society (ISTS), and the Quantitative Biomedical Sciences (QBS) program at Dartmouth. Previously I was a fellow at the Berkman Klein Center at Harvard University and a technical advisor to the non-profit startup Cortico.

+ View more


Engineer and Comp Science Ctr, Room 212
HB 6211


Computer Science


  • B.Sc. Massachusetts Institute of Technology
  • M.Sc. Massachusetts Institute of Technology
  • Ph.D. Massachusetts Institute of Technology
  • Fellow, The Berkman Klein Center for Internet & Society, Harvard University

Selected Publications

  • See the full list of my publications here

    Vijayaraghavan, P. & Vosoughi, S. (2022). TWEETSPIN: Fine-grained Propaganda Detection in Social Media Using Multi-View Representations. Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics.

    Liu, R., Zhang, G., Feng, X, & Vosoughi, S. (2022). Aligning Generative Language Models with Human Values. Findings of the Association for Computational Linguistics: NAACL 2022.

    Guo, X., & Vosoughi, S. (2022). A Large-Scale Longitudinal Multimodal Dataset of State-Backed Information Operations on Twitter. Proceedings of the International AAAI Conference on Web and Social Media, 16(1), 1245-1250.

    Liu, R., Gao, C., Jia, C., Xu, G., & Vosoughi, S. (2022). Non-Parallel Text Style Transfer with Self-Parallel Supervision. In International Conference on Learning Representations.

    Ma, W., Datta, S., Wang, L., & Vosoughi, S. (2022). EnCBP: A New Benchmark Dataset for Finer-Grained Cultural Background Prediction in English. In Findings of the Association for Computational Linguistics: ACL 2022, 2811-2823.

    Ma, W., Lou, R., Zhang, K., Wang, L., & Vosoughi, S. (2021). GradTS: A Gradient-Based Automatic Auxiliary Task Selection Method Based on Transformer Networks. In Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, 5621-5632.

    Liu, R., Wei, J., & Vosoughi, S. (2021). Language Model Augmented Relevance Score. Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), 6677–6690.

    Wang, L., Huang, C., Lu, Y., Ma, W., Liu, R., & Vosoughi, S. (2021). Dynamic Structural Role Node Embedding for User Modeling in Evolving Networks. ACM Transactions on Information Systems, 40(3), 1–21.

    Liu, R., Jia, C., Wei, J., Xu, G., Wang, L., & Vosoughi, S. (2021). Mitigating Political Bias in Language Models through Reinforced Calibration. Proceedings of the AAAI Conference on Artificial Intelligence, 35(17), 14857–14866. Best Paper Award.

    Liu, R., Wang, L., Jia, C., & Vosoughi, S. (2021). Political Depolarization of News Articles Using Attribute-Aware Word Embeddings. Proceedings of the International AAAI Conference on Web and Social Media, 15(1), 385–396.

    Liu, R., Xu, G., Jia, C., Ma, W., Wang, L., & Vosoughi, S. (2020). Data Boost: Text Data Augmentation Through Reinforcement Learning Guided Conditional Generation. Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP), 9031–9041.

    Vosoughi, S., Roy, D., & Aral, S. (2018). The spread of true and false news online. Science, 359(6380), 1146–1151. Featured as the Cover Story. 

    Vosoughi, S., Mohsenvand, M. 'Neo,' & Roy, D. (2017). Rumor Gauge: Predicting the Veracity of Rumors on Twitter. ACM Transactions on Knowledge Discovery from Data, 11(4), 1–36.

    Vosoughi, S., Vijayaraghavan, P., Yuan, A., & Roy, D. (2017). Mapping Twitter Conversation Landscapes. Proceedings of the International AAAI Conference on Web and Social Media, 11(1), 684–687.

    Vosoughi, S., Vijayaraghavan, P., & Roy, D. (2016). Tweet2Vec: Learning Tweet Embeddings Using Character-level CNN-LSTM Encoder-Decoder. Proceedings of the 39th International ACM SIGIR Conference on Research and Development in Information Retrieval, 1041–1044.

    Vijayaraghavan, P., Vosoughi, S., & Roy, D. (2016). Automatic Detection and Categorization of Election-Related Tweets. Proceedings of the International AAAI Conference on Web and Social Media, 10(1), 703–706.