Overview – week by week

Week 1: Kick Off

This week answers the following questions:

What does the term CSS mean?
Which principles underly a new CSS?
Which methods does CSS encompass?
How do we set up our computational workstation?

Week 2: Brief Intro to Python & Regexes

This week answers the following questions:

How can we run Python in RStudio using reticulate?
What are the basics of Python programming?
What are regular expressions and why are they powerful?
How can we use stringr to work with text patterns?

Week 3: Data Acquisition I

This week answers the following questions:

How is the web written and structured?
What are considerations in terms of law and ethics when scraping?
How do we acquire digital trace data via web scraping with rvest?
What are CSS selectors and how do they work?

Week 4: Data Acquisition II

This week answers the following questions:

How do we scrape dynamic web pages that use JavaScript?
How can we interact with forms and buttons using selenium?
What are APIs and how do we use them?
How do we make API calls with httr2?

Week 5: Data Acquisition III

This week answers the following questions:

What is Optical Character Recognition (OCR)?
How can we extract text from images and PDFs?
What is speech-to-text transcription?
How can we leverage these techniques for social science research?

Week 6: Data Acquisition IV

This week answers the following questions:

How do we digitize text using Tesseract?
How do we digitize speech using OpenAI Whisper?
What are best practices for data acquisition projects?
How do we plan our research projects?

Week 7: Student Project Week

This week is dedicated to working on your research projects in class.

Discuss your project ideas with peers and the instructor
Begin data acquisition for your research
Troubleshoot technical challenges
Form study groups with matching research interests

Week 8: Text as Data I

This week answers the following questions:

What do we mean by “text as data”?
What do we mean by “bag of words”?
How do we perform sentiment analysis?
What are TF-IDF, Named Entity Recognition (NER), and Part-of-Speech (POS) tagging?

Week 9: Text as Data II

This week answers the following questions:

What is supervised machine learning?
How can we train classifiers to categorize text?
What are best practices for supervised ML in social science?
How do we evaluate model performance?

Week 10: Text as Data III

This week answers the following questions:

What is unsupervised machine learning?
How does topic modeling work?
What can probabilistic topic models tell us about text corpora?
When should we use unsupervised vs. supervised approaches?

Week 11: Text as Data IV

This week answers the following questions:

How can we go beyond the “bag of words”?
What is the distributional hypothesis?
How can we measure semantic similarity between texts?
What are word embeddings and what do they capture?

Week 12: Text as Data V

This week answers the following questions:

What are transformer models like BERT?
How do these models revolutionize text classification?
What is transfer learning and why is it so powerful?
What is active learning and how can it reduce annotation burden?

Week 13: Text as Data VI

This week answers the following questions:

What’s the latest in Natural Language Processing with Large Language Models (LLMs)?
How can we use LLMs for information extraction?
What are local LLMs and when should we use them?
How do we move from codebooks to promptbooks?

Week 14: Presentation Preparation Week

This week is dedicated to preparing your final presentations.

Finalize your analyses and preliminary results
Prepare presentation slides (deadline: January 30, 6PM)
Review the peer review guidelines
Practice your 10-minute presentation

Week 15: Presentations & Wrap Up

This week features peer-reviewed presentations of your research projects.

Present your research (10 minutes)
Receive feedback from assigned peer reviewers (5 minutes)
Discuss next steps for your final paper
Reflect on what we’ve learned throughout the semester