Talk Less, Graph More: NLP, Networks and Hamilton Musical
summary
Builds a song-as-node corpus in Python with networkx, tokenizes lyrics with n‑grams, ranks phrases by TF‑IDF and enforces a minimum of four tokens to reduce noise, and defines edge weight as the sum of squares of phrase lengths over minimum song length plus a motive term; an example connection scores 462. The pipeline folds the graph into a word graph and a visibility graph, finds five standalone songs and coherent clusters, and the implementation produces interpretable narrative structure.
AI-written summary · about
chapters (8)
- 0:00Talk introduction
- 2:32Speaker intro
- 3:34Natural language processing basics for lyrics analysis
- 6:29Networks and graph types
- 7:57Building lyrics graph
- 10:26Hamilton as undirected graph
- 12:34Song progression analysis
- 14:42Summary
related talks
27mPythonic Metal
40mBuilding A Folk Music Recommendation System with LLMs
38mDynamics in Graph Analysis: Adding Time as a Structure for Visual and Statisti
36mGeorgia on my Mind: NLP Meets Social Network Analysis for Exploring New Domains
31mGraph-Based Machine Learning with Python
01h 41mGraph Intelligence: Enhance Reasoning and Retrieval Using Graph Analytics
43mGraphs are Everywhere
42mDynamics in Graph Analysis Adding Time as a Structure for Visual and Statistical