Skip to content
Nat Lee

Keyboard shortcuts

Turn these off if they get in the way of a screen reader or voice control. The setting is saved in this browser.

1
Home
2
Projects
3
About
4
Experience
/
Search projects
?
Show this panel

AI/ML

Sentiment Analysis Platform

Large-Scale NLP Processing System

Led the sentiment engine behind a company's social-listening products, reading more than three billion crawled posts. Lesson learned: the internet is mostly complaints.

Role
Senior Software Engineer
Period
2021.12 – 2023.04
Status
Completed
Theme
AI, vision & medical imaging
Sentiment Analysis Platform, screenshot 1

Overview

As the lead engineer for the sentiment analysis AI engine, I developed and maintained the core emotion detection model that processes data from web crawlers. The system analyzes sentiment from crawled content and outputs emotion classification results, which are then integrated with the company's flagship products—Keypo (大數據引擎) and DailyView (網路溫度計)—to provide users with comprehensive online sentiment and buzz analysis. The platform successfully processed over 3 billion data points with a 30% accuracy improvement, enabling real-time sentiment monitoring and trend analysis for business intelligence.

The problem

  • Processing 3+ billion data points
  • Real-time analysis requirements
  • Model accuracy optimization
  • System scalability

What I did

  • Developed and maintained the core sentiment analysis AI engine
  • Built data processing pipeline from web crawlers to emotion classification
  • Integrated sentiment analysis results with Keypo and DailyView products
  • Implemented distributed processing with Kubernetes for scalability
  • Optimized models using PaddlePaddle framework for 30% accuracy improvement
  • Built efficient data pipeline with Elasticsearch for real-time analysis

Results

  • Successfully deployed core sentiment analysis AI engine for company products
  • Processed over 3 billion data points from web crawlers
  • Achieved 30% improvement in emotion classification accuracy
  • Integrated sentiment analysis with Keypo and DailyView platforms
  • Enabled real-time online sentiment and buzz analysis for end users
  • Deployed scalable microservices architecture supporting high-volume processing

Features

  • Core sentiment analysis AI engine development
  • Web crawler data processing pipeline
  • Emotion classification and sentiment output
  • Integration with Keypo and DailyView platforms
  • Online sentiment and buzz analysis for users
  • Real-time sentiment monitoring
  • Scalable microservices architecture
  • AI, vision & medical imaging33 stars on GitHub

    QWOP with PPO

    A PyTorch PPO agent plays the real QWOP browser game through Playwright. Six evaluation races, six 100 m finishes. Grace was not part of the reward function.

    2019Completed
  • AI, vision & medical imaging4040 stars on GitHub

    Brain MRI Pipeline

    An end-to-end Nipype pipeline with FSL FAST, K-means and ANTs Atropos segmentation, tissue volumes, bias-correction metrics and an interactive 3D brain.

    2018Completed
  • AI, vision & medical imaging11 stars on GitHub

    Street Scene OCR

    Compare EasyOCR, RapidOCR and PaddleOCR on Traditional Chinese street signs, with text boxes, timings and a small public-domain benchmark.

    2026Completed