From Unstructured to Structured: Building Data Collections for East Asian Studies with AI
When and Where
Speakers
Description
The Cheng Yu Tung East Asian Library is actively developing the AI Innovation Series to support both library staff and the broader university community, including students, faculty, and researchers. For library staff, the series focuses on integrating AI into daily operations and special projects to enhance workflow efficiency and service delivery. For faculty, students, and researchers, the series offers insights into AI tools and methods that can enrich scholarship—particularly in East Asian Studies—and inspire innovation in academic research and teaching.
Required equipment and software:
A personal laptop (mobile phones are not recommended) ChatGPT (Plus or EDU version preferred; a registered non-Plus version is also acceptable), Claude, or other chatbots like Perplexity, Microsoft Copilot, or Google Gemini Google Sheets (personal account, ending with @gmail.com) Dify Account (to be registered during the workshop.
Workshop Two: From Unstructured to Structured: Building Data Collections for East Asian Studies with AI
This workshop is designed for East Asian Studies graduate students and faculty interested in integrating digital tools and methods into their learning and research processes. Participants will gain practical skills in utilizing AI-assisted tools for East Asian Studies research. Students, faculty, and researchers in the humanities more broadly may also find the workshop useful.
Date: Friday, January 17, 2025
Session 1: 10:00 AM – 12:00 PM
Lunch: 12:15 PM – 1:15 PM (Lunch provided to workshop participants) Session 2: 1:30 PM – 3:30 PM
RSVP: https://forms.gle/PCWAcBU7Uy8dxYox5
In these two two-hour hands-on workshops, participants will learn how to transform an unstructured corpus into structured data, making it suitable for databases or data analysis for both qualitative and quantitative approaches.
Throughout the session, participants will explore the following topics:
Understanding the nature and types of data Crafting effective prompts for AI tools Cleaning and organizing data using GenAI and Google Sheets Extracting relevant data from unstructured sources Generating metadata for structured datasets Performing basic data analysis and visualization.
