I turn qualitative customer data into psychological insight and strategic decisions.
Selected work
Probato
An independent project I started in 2024. It pulls apart meaning, stance, and moral-foundation signals in short, context-heavy reactions and turns them into evidence you can act on.
Frame numbers are unsupervised cluster IDs, not topic names or ranks.
Frame 7 is the dominant cluster, with 57,128 items. Its mean signals are harm 0.22, fairness 0.52, betrayal 0.47, authority 0.33, degradation 0.39, and liberty 0.18. The numeric ID carries no topic meaning on its own.
Platform shares of reactions scoring 3.0 or higher
In Naver News comments, 46.8% showed high fairness criticism, 41.2% high governance criticism, and 20.3% high exit intention; in Clien comments the shares were 43.7%, 35.7%, and 28.8%. The samples and expression styles differ too much to read as a simple platform ranking.
SNU MBA Applied Business Project
An MBA graduation project that pairs market reactions with online stakeholder data to compare cybersecurity crisis-response options.
From qualitative signals to strategic judgment
Qualitative analysis
I break irony, ridicule, stance, and context into units I can actually analyze.
Customer psychology
I read the psychological frames behind aversion and demands for accountability, not just whether sentiment leans positive or negative.
Data and AI
I tie collection, schemas, LLM-assisted labeling, embeddings, and evaluation into one reproducible workflow.
Strategy
I turn findings into options, priorities, the conditions for acting, and the limits of what they show.
Analysis with an implementation path
My background runs through ethics education, editorial work, an MBA, and data analysis. I draw on all of it to explain why customers react and what that reaction means for a decision.