About Me

Hello, I am a Ph.D student in the Computer Science and Engineering at Michigan State University. I received B.S. in Computer Science at Yonsei University. I am interested in applying Natural Language Processing (NLP) techniques to comprehend and analyze social problems such as social biases in large language models, biases in healthcare, and political framing in media.

Education

  • Ph.D in Computer Science and Engineering, Michigan State University, 2025 (expected)
    • Michigan State University Enrichment Fellowship
  • B.S. in Computer Science, Yonsei University, 2017

Publications

  • Michelle YoungJin Kim, Junghwan Kim, Kristen Johnson, “Race, Gender, and Age Biases in Biomedical Masked Language Models,” The 61st Annual Meeting of the Association for Computational Linguistics (ACL’23) (pdf)
  • Junghwan Kim, Michelle YoungJin Kim, Barzan Mozafari, “Provable Memorization Capacity of Transformers,” The Eleventh International Conference on Learning Representations (2023) (pdf)
  • Michelle YoungJin Kim, Junghwan Kim, Bryan Woosung Kim, Kristen Johnson, Jee-In Kim, “AsdClaims: Twitter Dataset of Claims on Autism Spectrum Disorder,” 1st International Workshop on Big Data Analytics for Health and Medicine (2022) (pdf)
  • Michelle Youngjin Kim, Kristen Johnson, “CLoSE: Contrastive Learning of Subframe Embeddings for Political Bias Classification of News Media,” COLING (2022) (pdf, GitHub)
  • Woojeong Jin, Dongjin Choi, Youngjin Kim, and U Kang, “Activity Prediction from Sensor Data using Convolutional Neural Networks and an Efficient Compression Method,” Journal of KIISE (2018) (pdf)

Internships

  • [Summer 2021, 2022] MedKit Korea
    • Seoul, Republic of Korea
      • Led the collection of social media data on Autism Spectrum Disorder (ASD) via keyword search, curated dataset through filtering and labeling, and published results at IEEE BDA4HM Workshop.
      • Collaborated with game developers to create scenarios for digital therapy game using language generation models.
      • Collaborated with the Jeju National University Hospital in Korea to build a fact-checking model on ASD using machine learning algorithms.

Projects

  • [Aug. 2020 - Dec. 2020] Legal Judgement Prediction
    • Course project for CSE 842 Natural Language Processing at Michigan State University, East Lansing, USA
      • Utilized summarization as a pre-processing method for legal judgement prediction.
      • Collected dataset for legal text summarization and legal judgment prediction tasks.
      • Written Report
  • [May 2018 - Sep. 2018] Building Lidar-Based Human Detection Technology
    • Samsung Electronics Co., Ltd. Seoul, Republic of Korea
      • Developed a Lidar-sensor environment for data acquisition.
      • Acquired and extracted data for the experiment, using a Lidar sensor.
  • [Sep. 2017 - Apr. 2018] Building Energy Optimization Technology
    • Samsung Electronics Co., Ltd. Seoul, Republic of Korea
      • Developed a Deep Residual Net-based model for predicting human activities such as walking, resting, and teaching.
      • Collected video for motion detection and sensor data for the detection of changes in temperature and sound and conducted the pre-processing of multimodal data.
      • Managed the model repository and the website that displayed real-time predictions of the lab space activity.
  • [Sep. 2016 - May 2017] Parallelization of Laminar-IR
    • Capstone project at Yonsei University, Seoul, Republic of Korea
      • Implemented unfolding of stream graphs onto multicore platforms, using double buffering technique and barriers for synchronization.
  • [Sep. 2016 - Dec. 2016] Recommendation System for the Best-Fit Keyboard Layout
    • Course project at Yonsei University, Seoul, Republic of Korea
      • Implemented a deep learning model that recommends a mobile keyboard layout.
      • Acquired log file data of mobile users.

Additional Experience

  • [Jan. - Dec. 2023] Engineering Graduate Leadership Fellows Program
    • Organized Graduate Women Lunches. Faced backlash across the College but worked with the College of Engineering Graduate Studies to overcome the difficulties and continue hosting the events.
    • Organized social events for students’ well-being, including Bagels Before Break every semester and a coffee drop-in event after the shooting on campus.
    • Assisted the organization of the Engineering Graduate Research Symposium that celebrates and encourages research across all College units.
  • [Apr. 2022] CRA-WP Grad Cohort for Women

Teaching Experience

  • [Fall 2023] Teaching Assistant, Introduction to Machine Learning
    • Michigan State University, East Lansing, MI, USA
  • [Spring 2018] Teaching Assistant, Introduction to Data Mining
    • Seoul National University, Seoul, Republic of Korea
  • [Summer 2014] Teaching Assistant, After-school computer science program
    • Geumok Elementary School, Seoul, Republic of Korea
  • [2009-2011] Teaching Assistant, SAT academy
    • IvyPlan, Seoul, Republic of Korea
  • [2006-2007] English Tutor, Voluntary program
    • Domestic violence shelter, Seoul, Republic of Korea

Skills

  • Programming Languages: Python, C++, C, Java
  • Libraries: PyTorch, TensorFlow, NumPy, SciPy, Pandas

Relevant Coursework

  • [Spring 2021] Numerical Linear Algebra
  • [Fall 2020] Natural Language Processing
  • [Spring 2018] Topics in Algorithms (Data Compression)
  • [Spring 2018] Introduction to Computer Vision
  • [Fall 2017] Deep Learning
  • [Fall 2017] Machine Learning
  • [Fall 2015] Discrete Mathematics