Research Proposal

DSAI,Fall 2025

简介

  • This project is a crucial component of the course assessment. It evaluates students’ ability to collect, clean, and analyze economic and social big data using the research methods and AI tools learned in class.

  • The project comprises 90% of the total grade, divided between a mid-term research plan (50%) and a final results presentation (40%).

  • Students will work in teams to present a research proposal mid-semester and a final report at the end of the semester. Each group will jointly finish the project,complete with supporting data and code. And the grade will be assigned to members of the group equally.(If you cannot find a partner, don’t hesitate to seek assistance from the teaching assistant or instructor.)

研究计划上交日期(Deadline for Research Proposal)

时间 内容
9/25 组成 \(\textcolor{blue}{team}\)
10/9 选择 \(\textcolor{blue}{project}\) 并在Github上建立Repository
10/30 上传 \(\textcolor{blue}{期中研究计划}\) and all scripts 到Github
12/26 上传 \(\textcolor{blue}{期末研究報告}\) and all scripts 到Github

For A Data-driven Research Proposal (数据研究计划内容指南）

  • You could choose one of the following projects or propose your own topic related to data science and AI. The key is to demonstrate your ability to apply the concepts and tools learned in class to a real-world problem.

  • Each project should include the following components:

    • Data Source: Identify the source of your data (e.g., APIs, web scraping, OCR tools).
    • Data Acquisition: Describe how you will collect the data.
    • Data Cleaning: Outline the steps you will take to clean and preprocess the data.
    • Descriptive Analysis: Explain the initial analysis you will perform to explore the data.
    • Visualization: Plan how you will visualize the data to illustrate your findings.

Project A - Satellite Data or Other Remote Sensing Data and Spatial Analysis

  • Data Source: NASA, Google Earth Engine, or other satellite data platforms.
  • Data Acquisition: Use APIs or web scraping to collect relevant satellite data.
  • Data Cleaning: Process and clean the collected data to ensure quality.
  • Descriptive Analysis: Perform initial analysis to explore data patterns and trends.
  • Visualization: Create visual representations of the data to illustrate findings.

Project B - Social Media Data Acquisition and Descriptive Analysis

  • Data Source: Baidu Index and Baidu Wikipedia.
  • Data Acquisition: Use or web scraping to collect relevant information.
  • Data Cleaning: Process and clean the collected data to ensure quality.
  • Descriptive Analysis: Perform initial analysis to explore data patterns and trends.
  • Visualization: Create visual representations of the data to illustrate findings.

Project C - OCR Data Acquisition and Descriptive Analysis

  • Data Source: Gazetteer PDFs or other text-based documents.
  • Data Acquisition: Use OCR tools (e.g., Baidu PaddlePaddle) to extract text from images or PDFs.
  • Data Cleaning: Process and clean the extracted text data to ensure quality.
  • Descriptive Analysis: Perform initial analysis to explore data patterns and trends.

Project D - Big data analysis: Job Posting Data Cleanning and Descriptive Analysis

  • Data Source: Job posting websites (e.g., Zhaopin, 51job).
  • Data Cleaning: Process and clean the collected job posting data to ensure quality.
  • Descriptive Analysis: Perform initial analysis to explore data patterns and trends.
  • Visualization: Create visual representations of the data to illustrate findings.