Aeri Cho

Hi. I’m a Ph.D. student at the Human-Computer Interaction Lab at Seoul National University, advised by Professor Jinwook Seo.

My research focuses on making complex fields like high-dimensional data and model explainability more human-friendly and accessible through interactive visualization and intuitive data interactions, enabling people to gain meaningful insights.

I received my B.S. in Computer Science and Engineering from Seoul National University in 2021.

Research Interests

Interactive Data Analysis

HCI

Visual Analytics

Explainable AI

High-Dimensional Data

Selected Publications View all publications→

VISxAI

Workshop

LIME & SHAP Explained: From Computation to Interpretation

Aeri Cho, Jeongmin Rhee, Seokhyeon Park, and Jinwook Seo

Workshop on Visualization for AI Explainability (VISxAI) (at IEEE VIS), Oct 2025

Website
IEEE TVCG

Journal

Towards More Explainable Nonlinear Dimensionality Reduction: A Feature-Driven Interaction Approach

Aeri Cho, Hyeon Jeon, Kiroong Choe, Seokhyeon Park, and Jinwook Seo

IEEE Transactions on Visualization and Computer Graphics, Oct 2025

Abs

Nonlinear dimensionality reduction (NDR) techniques are widely used to visualize high-dimensional data. However, they often lack explainability, making it challenging for analysts to relate patterns in projections to original high-dimensional features. Existing interactive methods typically separate user interactions from the feature space, treating them primarily as post-hoc explanations rather than integrating them into the exploration process. This separation limits insight generation by restricting users’ understanding of how features dynamically influence projections. To address this limitation, we propose a bidirectional interaction method that directly bridges the feature space and the projections. By allowing users to adjust feature weights, our approach enables intuitive exploration of how different features shape the embedding. We also define visual semantics to quantify projection changes, enabling structured pattern discovery through automated query-based interaction. To ensure responsiveness despite the computational complexity of NDR, we employ a neural network to approximate the projection process, enhancing scalability while maintaining accuracy. We evaluated our approach through quantitative analysis, assessing accuracy and scalability. A user study with a comprehensive visual interface and case studies demonstrated its effectiveness in supporting hypothesis generation and exploratory tasks with real-world data. The results confirmed that our approach supports diverse analytical scenarios and enhances users’ ability to explore and interpret high-dimensional data through interactive exploration grounded in the feature space.
IEEE PacificVisConference

Automated Pipeline for Detecting and Analyzing Misleading Visual Elements

Min Hyeong Kim, Yumin Song, Yungun Kim, Aeri Cho, Soohyun Lee, Hyeon Jeon, and Jinwook Seo

2025 IEEE 18th Pacific Visualization Conference (PacificVis), Jun 2025

Abs

Data visualizations can sometimes misrepresent the underlying data, leading to misleading interpretations. However, existing systems fail to precisely identify which parts of a visualization contribute to misleading interpretations, leaving users uncertain about the misalignments. To address this issue, we develop a pipeline that automatically identifies the misleading parts within a visualization. Given an image file, our pipeline first detects graphical components of the visualization, converting them into structured objects. We then apply an algorithm to pinpoint misleading objects and explain how they contribute to distortions in interpretation. Our user study confirms that our pipeline accurately identifies misleading visualization designs, outperforming previous baselines. We also find that our pipeline supports participants in developing revision strategies to improve misleading visualizations.

Experiences

Work

Jan - Feb 2020

Undergraduate Research Intern
Human-Centered Computer Systems Lab, Seoul National University

Jul - Aug 2019

Software Engineering Intern
Web UI Developement for Web Browser, Naver Corp.

Aug - Dec 2018

Undergraduate Research Opportunities Program (UROP)
Intelligent Data System Lab, Seoul National University .

Talks

Nov 2025

IEEE VIS 2025, workshop on Visualization for AI Explainability (VISxAI), Vienna, on the research LIME & SHAP Explained: From Computation to Interpretation

Oct 2024

KoreaVis 2024, Seoul, on the research Towards More Explainable Nonlinear Dimensionality Reduction: A Feature-Driven Interactive Approach

Oct 2023

IEEE VIS 2023, Melbourne, on the research paper ZADU: A Python Library for Evaluating the Reliability of Dimensionality Reduction Embeddings

Jun 2023

Tech Talk at Naver Corp, on Interactive Exploration of Nonlinear Dimensionality Reduction

Teaching

2025 Spring

Woori Financial Group Data Expert, Seoul National University
Data Visualization

2022 Spring

Samsung AI Expert Program (NPEX), Seoul National University
Data Visualization

2022 - 2025

Samsung DS² Program, Seoul National University
Data Visualization

2021 Fall

Digital Computer Concept and Practice, Seoul National University
Python Programming

Service

Apr 2023

Student Volunteer, IEEE PacificVis 2023

Contact

Feel free to contact me for research discussions, collaborations, opportunities, or anything else!