Lingshu Hu

Professor Hu joined the faculty of the Williams School in September 2021. With a PhD in computational journalism and an MS in computer science, his primary teaching interests include making data analytics accessible to students in the social sciences and helping students master storytelling skills with data analytics and visualization.

Professor Hu’s research focuses on developing computational methods—such as machine learning, deep learning, and natural language processing—to examine patterns and effects of communication in computer-mediated environments. He also develops R and Python software to facilitate social science research. In addition to his research, Professor Hu is serving as the 2024-2025 Vice President of the Social Media Analytics Section at the INFORMS Annual Meeting.

Education

• Ph.D. in Journalism (Computational Methods), University of Missouri, School of Journalism (2021)
• M.S. in Computer Science, University of Missouri, Department of Electrical Engineering & Computer Science (2022)
• M.S. in Gender, Media, and Culture, London School of Economics and Political Science (2012)

Research

• Machine Learning, Deep Learning, and NLP
• Communication Patterns and Effects
• Social Media Analytics
• Social Identities
• Digital Public

Teaching

• BUS 202 - Fundamentals of Business Analytics
• BUS 306A - Applied AI and Machine Learning
• INTR 202 - Applied Statistics
• BUS 306D - User Generated Content: Analytics and Insights

Selected Publications

• Wang, W., Li, C., Hu, L., Pang, B., Balducci, B., Marinova, D., Gordon, M., & Shang, Y. (2024). Recognizing and Predicting Business Communication Outcomes Using Local LLMs. The Proceedings of the 2024 IEEE International Conference on Information Reuse and Integration for Data Science (IRI). 
  
  
• Hu, L. (2024). Mobilization, self-expression or argument? A computational method for identifying language styles in political discussion on Twitter. Online Information Review. https://doi.org/10.1108/OIR-10-2022-0545 
  
  
• Hu, L. (2023). A two-step method for classifying political partisanship using deep learning models. Social Science Computer Review. https://doi.org/10.1177/08944393231219685.
   
• Xu, M., Hu, L., & Hinnant, A. (2023). Pseudo-events: Tracking mediatization with machine learning over 40 years. Computers in Human Behavior, 144, 107735.
  
  
• Xu, M., Hu, L., & Cameron, G. T. (2023). Tracking moral divergence with DDR in presidential debates over 60 Years. The Journal of Computational Social Science, 6, 339–357.

• Hu, L., Li, C., Wang, W., Pang, Bin., & Shang, Y. (2022). Performance Evaluation of Text Augmentation Methods with BERT on Small-sized, Imbalanced Datasets. The Proceedings of the 2022 IEEE International Conference on Cognitive Machine Intelligence (CogMI).
  
  
• Li, C., Wang, W., Balducci, B., Hu, L., Gordon, M., Marinova, D., and Shang, Y. (2022) Deep Formality: Sentence Formality Prediction with Deep Learning. The Proceedings of the 2022 IEEE International Conference on Information Reuse and Integration for Data Science. 
  
  
• Zhang, W., Hu, L., & Park, J. (2022). Politics go “viral”: A computational text analysis of crisis attribution regarding the COVID-19 pandemic. Social Science Computer Review. 
  
  
• Hu, L., Kearney, M. W., & Frisby, C. M. (2021). Tweeting and retweeting: Gender discrepancies in discursive political engagement and influence on Twitter. Journal of Gender Studies. 
  
  
• Hu, L. (2021). Self as brand and brand as self: A 2x2 dimension conceptual model of self-branding in the digital economy. Journal of Internet Commerce, 20(3), 355–370. 
  
  
• Hu, L., & Kearney, M. W. (2021). Gendered tweets: Computational text analysis of gender differences in political discussions on Twitter. Journal of Language and Social Psychology, 40(4), 482–503.