Dongjin Choi

I am a Ph.D.candidate in Computational Science and Engineering at Georgia Institute of Technology, advised by Professor Haesun Park.
My research interests include Transfer Learning, Representation Learning, AI-Human Alignment, and Text Analytics with a particular focus on cross-domain applications.
I have conducted extensive research in knowledge graph mining, recommender systems building, and interactive visualization. 

I've collaborated with industry and research leaders, including Kaiser Permanente, Upstage, and Megagon Labs, contributing to projects that synergize academic research with real-world applications.

News

[Dec 2023]: Awarded Best Paper at the BigData 2023 Conference.
[Dec 2023]: Received the Travel Award at the BigData 2023 Conference.

Educations

@ Georgia Institute of Technology, Atlanta, GA, USA, Aug 2018 - Present

M.S. in Computational Science and Engineering

@ Georgia Institute of Technology, Atlanta, GA, USA, Aug 2018 - May 2022

B.S. in ECE (Minor: CSE)

@ Seoul National University, Seoul, Korea, Mar 2011 - Feb 2018

Experiences

AI Research Engineer Intern

@ UpstageKorea, Summer 2021
  - Mentor: Hwalsuk Lee
  - Developed a data cleansing system for OCR annotated data to enhance quality and reliability

Research Scientist Intern

@ Megagon LabsMountain View, CA, May 2020 - Aug 2020
  - Mentors: Çağatay Demiralp, Sara Evensen

  - Proposed a system for data programming by demonstration for span-level annotation

Data Science Intern

@ NAVER Corp., Seoul, Korea, Apr 2018 - Jul 2018 

Publications

최최최종_대지-1-사본

WellFactor [New]

WellFactor: Patient Profiling using Integrative Embedding of Healthcare Data

Dongjin Choi, Andy Xiang, Ozgur Ozturk, Deep Shrestha, Barry Drake, Hamid Haidarian, Faizan Javed, Haesun Park

BigData
 2023   [PDF]
Best Paper Award

최최최종_대지-1

Healthcare Embedding [New]

Patient Clustering via Integrated Profiling of Clinical and Digital Data


Dongjin Choi, Andy Xiang, Ozgur Ozturk, Deep Shrestha, Barry Drake, Hamid Haidarian, Faizan Javed, Haesun Park

CIKM Short 2023   [PDF]

무제-1_대지-1

McVis

Co-embedding Multi-type Data for Information Fusion and Visual Analytics

Dongjin Choi, Barry Drake, and Haesun Park

Fusion 2023   [PDF]

NLP-Loop-10

HITL-NLP Survey

Putting Humans in the Natural Language Processing Loop: A Survey

Zijie J. Wang, Dongjin Choi, Shenyu Xu, Diyi Yang

EACL Workshop on Bridging HCI and
NLP 
2021   [PDF]

TopicSifter-03

TopicSifter 

TopicSifter: Interactive Search Space Reduction Through Targeted Topic Modeling 

Hannah Kim, Dongjin Choi, Barry Drake, Alex Endert, Haesun Park 

IEEE VIS 2019   [PDF] 

Zoom-SVDline

Zoom-SVD

Zoom-SVD: Fast and Memory Efficient Method for Extracting Key Patterns in an Arbitrary Time Range

Jun-gi Jang, Dongjin Choi, Jinhong Jung, U Kang


CIKM 2018   [PDF]   [Homepage]

Awards & Honors

Best Paper Award

@ BigData 2023Dec 2023
   - Selected as the best research paper

Travel Grant Award

Humantech Paper Award (Bronze prize, Co-author)

@ Samsung, Feb 2017
   - Included in the top 6 in 'Computer Science & Engineering' division

Best term paper award in 'Writing in Science & Technology'

@ Seoul National University, Dec 2015   paper (written in Korean)
  - 1st place among 50 teams
  - The paper proposed a new design for motorcycle helmet shield to reduce driver's air pollutant inhalation
  - I drew the blueprint for 3-D printing and implemented Arduino experiment code

Projects

Screen-Shot-2022-02-18-at-2.00.12-PM-1-01

OCR Annotation Tool

Internship Project in Upstage AI,  May 2021 - Aug 2021

Boosted OCR Annotation process with the interactive user interface by validating and annotating labels at the same time

debatevis-09

DebateVis

Information Visualization term project (CS7450), Aug 2019 - Dec 2019

Interactively visualized 2019 democratic presidential debate

- Try Demo

People-flow-recognition

People Flow Recognition

People flow recognition for intelligent building systems (IBS), Sovico, Samsung, Sep 2017 - Jan 2018

Implement a pedestrian simulator (watch simulation video)

Deep-learning-termline

Deep Learning Term Project

Deep learning term project, Seoul Nathional University, Mar 2017 - June 2017

Term project for graduate deep learning course @SNU

Developed CNN model for human identification on image using transfer learning technique