Research Intern

09/2022 ~ 01/2023

Data Cleaning
Data Visualization
NTHU Institutional Research Center logo

NTHU Institutional Research Center

Hsinchu

Cleaned and integrated approximately 3,000 composite data records, used SBERT models for text vectorization analysis, and built course knowledge graphs with Gephi, Excel, and Python to visualize relationships between courses and departments.

Research Intern
2022/09 ~ 2023/01

Research Intern


# Data Collection/Preprocessing
# Text Mining
# Text Analysis
  • Extracted, cleaned, and integrated approximately 3,000 composite data records from various campus data sources to ensure data quality for subsequent analysis.
  • Used SBERT (Sentence-BERT) to vectorize course information into numerical representations for semantic similarity analysis.
  • Applied clustering analysis techniques to group similar courses and departments, revealing relationships across different academic fields.
  • Visualized analysis results as course knowledge graphs using Gephi, helping the Institutional Research Center understand and communicate research findings.