Japanese NLP Sentiment Analysis of Student Project Feedback

Natural Language Processing, Education Analytics, Japanese BERT

Japanese NLP Sentiment Analysis
Image: Japanese NLP Sentiment Analysis (2023–2025)

Project Overview

This project applies a deep learning–based natural language processing approach to analyze Japanese student feedback collected via Google Forms from project-based English classes, using a pretrained Japanese BERT model.

The analysis focuses on identifying students' favorite and least favorite projects, reasons for their preferences, and suggestions for improvement. The goal is to extract actionable insights to enhance curriculum design and student engagement.

An earlier exploratory version (2023) focused on morphological analysis and keyword extraction. In 2025, the project was redesigned to use Japanese Sentence-BERT embeddings and unsupervised clustering to identify latent semantic themes in improvement feedback.

Feedback Analysis Data

Key Findings

Project Popularity

  • Most favored: Country Presentation, Skit Festival
  • Least favored: Demonstration Dialogue
  • Skit Festival appears frequently in both categories, suggesting polarized experiences.

Reasons for Favorite Projects

  • Cultural learning opportunities
  • Creative expression
  • Autonomous and exploratory work

Areas for Improvement

  • Time management constraints
  • Project difficulty calibration
  • Clearer instructions and expectations

Percentage Distribution of Favorite and Least Favorite Projects

Word Cloud Analysis

Favorite Project Reasons

Favorite Project Word Cloud

Improvement Suggestions

Improvement Suggestion Word Cloud

BERT-Based Semantic Clustering of Improvement Feedback

Identified Clusters and Themes

Cluster Semantic Theme Description
Cluster 1 Practice Time & Preparation Requests for longer rehearsal periods and collaboration time.
Cluster 0 Task Structure & Instruction Clarity Need for clearer instructions, examples, and constraints.
Cluster -1 Miscellaneous Feedback Low-frequency or project-specific comments.

Cluster Distribution by Project

Favorite Project Misc. Structure Practice
Demonstration Dialogue400
Country Presentation36113
Skit Festival3785
Interview Speech471

Technical Summary

Data Science Skills

  • Natural Language Processing
  • Data Cleaning & Analysis
  • Visualization

Programming

  • Python
  • Jupyter Notebook
  • Google Colab

Libraries & Tools

  • Pandas
  • Matplotlib & Seaborn
  • Hugging Face Transformers

View the Project

View Source Code

Data Privacy Notice
All student responses were anonymized and analyzed in aggregate following institutional privacy guidelines.