Workshop Series on Web Scraping and Open-Source Large Language Models

The Department of Communication and Technology at National Yang Ming Chiao Tung University hosted the H&J Computational Communication Workshops Series on 24 June 2026.

The workshop series introduced foundational skills for digital research and generative AI applications in communication and the social sciences. Participants with some prior experience in Python or R could benefit from that background, but no programming experience was required. Complete example code was provided to support beginners throughout the workshops.

Web Scraping Workshop

Time: 12:30–14:30

This session introduced the fundamentals of collecting data from publicly accessible websites. It covered webpage structure, basic HTML, methods for extracting online data, and techniques for organising collected information into formats suitable for research analysis.

Web Scraping Workshop

Open-Source Large Language Models Workshop

Time: 15:00–17:00

This session introduced the basic concepts and applications of open-source large language models for researchers in the social sciences and humanities. Topics included commonly used models and tools, prompt design, and the use of open-source language models in research, text analysis, and teaching.

Open-Source Large Language Models

Event Information

Course materials are available here.

Speaker

Justin Chun-ting Ho is an Assistant Professor in the Department of Communication and Technology at National Yang Ming Chiao Tung University. His research focuses on computational communication methods and political communication. He previously held research positions at Sciences Po, Academia Sinica, and the University of Amsterdam, and has published in international academic journals. He also promotes open science and reproducible research and develops open-source tools for academic research.