Fall 2025

Computational Social Science Series – Fall 2025

October 3 | 12-1:30pm | PUP 438
Advancing Social Science Research: A Workshop Series on AI, LLMs, and Computational Methods
“Introduction to R, R Projects, R Markdown and the Basics of LLMs”
Dr. Eric Stokan, Director, CS3 and Associate Professor, Department of Political Science

Session one

  • Install and set up R and RStudio

  • R fundamentals: objects, vectors, data frames, scripts, packages (tidyverse)

  • R Markdown/Quarto: document structure, code chunks, rendering to HTML/PDF

  • LLMs 101: what they are, common research use cases, and calling them through an R package called ellmer.

Takeaways

  • A working R/RStudio environment

  • A template R Markdown report you can reuse

  • A checklist for responsible LLM use in research

November 5 | 12-1:30pm | Commons 329
Advancing Social Science Research: A Workshop Series on AI, LLMs, and Computational Methods
“Inductive Analysis of Texts with Embeddings”
Dr. Dustin Stoltz, Assistant Professor of Sociology and Cognitive Science at Lehigh University

Word or text embeddings are a central component in modern language models, including those powering generative AI. Embeddings represent word meanings as positions in space, where words that are closer together are used in similar contexts or evoke similar concepts — even if those words never actually co-occur. We navigate the meaning space created by embeddings directly using basic arithmetic, and in doing so, explore how meaning changes overtime or how meaning differs between different collections of texts.

Dustin Stoltz is an Assistant Professor of Sociology and Cognitive Science at Lehigh University.  He studies a variety of topics in cultural and economic sociology and specializes in computational methods.  Five copies of his recently published book Mapping Texts: Computational Text Analysis for the Social Sciences (coauthored by Marshall Taylor) was raffled off to workshop registrants.

November 7 | 12-1:30pm | PUP 438
Advancing Social Science Research: A Workshop Series on AI, LLMs, and Computational Methods
“Dealing with unstructured data (text, images), APIs, and API calls to LLMs”
Dr. Eric Stokan, Director, CS3 and Associate Professor, Department of Political Science

In this session we:
  1. Used the R programming language to work with unstructured data (text and images)
  2. Used OpenAI (makers of ChatGPT) to analyze unstructured data through an API
  3. Compared LLMs to other Natural Lnaguage Processing techniques (topic models, Named Entity Recognition)
  4. Discussed improved ways to prompt LLMs

December 12 | 12-1:30pm | PUP 438
Advancing Social Science Research: A Workshop Series on AI, LLMs, and Computational Methods
“Prompt-engineering and Fine-tuning in R”
Dr. Eric Stokan, Director, CS3 and Associate Professor, Department of Political Science

This session focused on the following topics:

1. Prompt engineering techniques
2. Discussion of fine-tuning techniques
3. Evaluation techniques for estimating the effectiveness of LLMs and LRMs