12 sessions · Fall 2026
Lectures
Introduction to text as data
What text data is, why it matters for business, and the basic steps for preparing text for analysis
Bag-of-words, TF-IDF, and cosine similarity
Turning text into numbers: document-term matrices, TF-IDF weighting, and comparing documents with cosine similarity
Bag-of-words-based methods
Dictionary-based approaches, text regression and classification, and topic modelling
Learning from prediction 1: n-gram language models
N-grams, character-level language models, and the fundamentals of next-token prediction
Practical day 1
Hands-on workflows with NLTK, scikit-learn, and Gensim — POS tagging, TF-IDF, and LDA topic models — plus guidance on the assignments
Learning from prediction 2: word embeddings
Pointwise mutual information, word embeddings, and what you can do with vector representations of words
Introduction to LLMs and tokenization
A critical introduction to large language models, and why tokenization shapes everything they can and cannot do
Attention and transformers
The attention mechanism, the transformer architecture, and why it dominates modern NLP
LLM input/output, training, and fine-tuning
How LLMs are specified, estimated, and adapted — pre-training, fine-tuning, and what it means for applied work
Practical day 2
Hands-on workflows with embeddings and LLMs, plus guidance on the remaining assignments
Prompt engineering, alignment, and summary
Getting the most out of pre-trained LLMs, how and why models are aligned, and a synthesis of the course
Mini-project presentations and feedback
Group presentations of the assignments with questions and feedback