Investigating with AI

The course bridges the gap between traditional social science research and contemporary AI capabilities, empowering students to gather, transform, and analyze textual data at scale - turning them into active investigators who can extract meaningful patterns from the digital noise that surrounds us.

Day 1: Welcome, intro, course scope, logistics; state of LLMs; hands on : data analysis on google colab

• Welcome to the course

Day 2: LLMs, JSON and pandas

• LLMs, JSON and pandas

Day 3: APIs

How the Web works; APIs; The Wikipedia API; The NYT API, Duckduckgo API

• APIs

Day 4: NLP with Spacy: NER, POS, topic modeling, text classification, tokens, stop words, lemmatization, …; NYT API; more python;

• classic NLP

Day 5: embeddings; LLMs; RAG; Spacy.io;

• modern NLP

Day 6: from LLMs to Agents

• LLMs to Agents

Day 7: Data visualization and inference

• Data visualization
• inference

day 8 networks, scraping day 9 machine learning, deep learning day 10 streamlit, github day 11 buffer day 11 project presentation