About Me

Hello! I am Migyeong Kang, a Ph.D. candidate in Applied Artificial Intelligence at Sungkyunkwan University (SKKU), advised by Prof. Jinyoung Han. I expect to graduate in February 2027.

My research focuses on natural language processing (NLP) for mental health, particularly mental disorder detection using deep learning and large language models. Building on this work, I aim to develop AI systems for mental health support and counseling, with an emphasis on human–computer interaction (HCI) and human–AI alignment.

I was a Visiting Scholar at Indiana University Bloomington from September 2024 to March 2025, working with Prof. Haewoon Kwak and Prof. Jisun An.

You can find my research on the Publications page and download my CV.

News

  • 🎉 2026: Two of our papers, Same Symptoms, Different Severity?: Investigating Gendered Cue Effects on LLMs in Depression Severity Assessment and SCENE: A Scenario Completion Benchmark for Measuring Social Bias in Large Language Models, have been accepted to Findings of EMNLP 2026!
  • 🎉 September 2026: Our paper, SCENE: A Scenario Completion Benchmark for Measuring Social Bias in Large Language Models, was featured in University Journal. Happy to see our research reaching a wider audience!
  • 🎉 2026: Excited to share that SynSym: A Synthetic Data Generation Framework for Psychiatric Symptom Identification has been accepted to the KDD 2026! Read the paper.

Selected Publications

Overview of the CURE framework: feature extraction, model predictions, and uncertainty-aware decision fusion.

CURE: Context- and Uncertainty-Aware Mental Disorder Detection

Migyeong Kang, Goun Choi, Hyolim Jeon, Jihyun An, Daejin Choi*, and Jinyoung Han*

Conference on Empirical Methods in Natural Language Processing (EMNLP 2024)

SynSym framework for symptom concept expansion, synthetic expression generation, evaluation, and symptom identification.

SynSym: A Synthetic Data Generation Framework for Psychiatric Symptom Identification

Migyeong Kang, Jihyun Kim, Hyolim Jeon, Sunwoo Hwang, Jihyun An, Yonghoon Kim, Haewoon Kwak, Jisun An, and Jinyoung Han*

ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD 2026)

Counterfactual evaluation of depression severity predictions using neutral, male, and female gender cues.

Same Symptoms, Different Severity?: Investigating Gendered Cue Effects on LLMs in Depression Severity Assessment

Migyeong Kang**, Sihyeon Yang**, Minseok Kim, Jihyun An*, Haewoon Kwak*, and Jinyoung Han*

Findings of the Association for Computational Linguistics (EMNLP 2026)

View all publications