I am a fifth-year Ph.D. student in Computer Science at Virginia Tech, working with my advisor Eugenia Rho. My research focus on Computational Social Science (CSS), Human–computer interaction (HCI), AI-mediated communication (AIMC) and the use of Natural Language Processing (NLP) technologies to explore decades of closed-caption data from major news outlets [2023a], online community interactions [2024a, 2024b, 2025a， 2025b], and public health and mental health issues [2024c,2025c].
I received MS in Computer Science from George Mason University, under the instruction from Gheorghe Tecuci. My research contributed to multiple research projects involving large language models and their applications in social media discourse.
📊 Research Highlights
- Using AI to Study How Social Media Discussions Affect Public Health
Our research introduces a new approach using LLMs (i.e., ChatGPT) to understand how discussions about health measures, such as COVID-19 restrictions, on social media influence public health outcomes like vaccination rates. By tracking “gists” in online conversations, we demonstrate how language patterns can predict real-world health trends, offering valuable insights for improving public health communication. - How TV News Shapes Social Media Discussions
Our research analyzes how language used by major news channels, such as CNN and Fox News, influences conversations on social media. Our research compares TV news content with social media posts and shows that the way news is presented can deepen political polarization online, especially after 2016. - Why People Do or Don’t Respond to Hate Speech Online
Our study investigates the motivations and barriers that influence people’s willingness to respond to hate speech online. By surveying hundreds of participants, our research finds that those who have been targets of hate are more likely to respond, while younger individuals, women, and regular witnesses to hate speech often hesitate due to fears of retaliation. - CounterQuill: An AI Tool to Help People Write Responses to Hate Speech
Our research introduces CounterQuill, an AI tool designed to assist users in creating empathetic and effective responses to hate speech. Our study evaluates the tool through a step-by-step process that helps users understand hate speech, brainstorm counterspeech, and co-write their final responses.
📰 News
💡 Paper accepted by EMNLP 2025. – A Multi-Level Benchmark for Causal Language Understanding in Social Media Discourse
💡 Paper accepted by IEEE VL/HCC 2025. – Designing Human-AI Collaboration to Support Learning in Counterspeech Writing
💡 Won the Computer Science Scholars and Pratt Fellowship
This scholarship was created in 1967 through a gift by John Lee Pratt and represents the funding source for the Dean’s Scholar Award.
🌍 Scientific American posted the news related to our paper: AI Tool Predicts Whether Online Health Misinformation Will Cause Real-World Harm
🌍 Virginia Tech has posted news related to our paper: Study traces an infectious language epidemic
💡 Paper accepted by ACM CHI 2024. – Leveraging Prompt-Based Large Language Models: Predicting Pandemic Health Decisions and Outcomes Through Social Media Language
🌍 Forbes has posted news related to our paper: Be Careful What You Feed Your Head
Xiaohan Ding 