Tips, Tricks and Topics in Text Analysis
summary
Hands‑on pipeline that loads ~300 Australian news articles and a 20‑newsgroups subset, uses spaCy for lemmatization, POS and NER, builds bigrams, creates a gensim dictionary (5,329 unique tokens) and a bag‑of‑words, runs gensim LDA for topic modeling, converts to TF‑IDF + SVD then trains classifiers (GaussianNB, SVM) with scikit‑learn, and finally trains a character‑level generator with Keras LSTM; code and notebooks live in the linked GitHub repo and the examples run end‑to‑end.
AI-written summary · about
chapters (9)
- 0:00Introduction
- 10:15Why text analysis is useful
- 24:17Computational linguistics with spaCy
- 31:26Vectorizing text for ML
- 48:08Text cleaning and lemmatization
- 50:13Topic modeling with Jensen
- 1:00:34Text classification with scikit-learn
- 1:17:53Deep learning for text generation
- 1:26:23Summary
related talks
01h 14mIntroduction to NLP
30mKick-Start your Understanding of Machine Learning with Python
02h 19mWorkshop: Demystifying Natural Language Processing using Python (Scikit-Learn/ Keras)
48mIntroduction to Natural Language Processing with Python
25mInventing Curriculum using Python and spaCy
01h 39mNatural Language Processing (NLP) in Python - From Zero to Hero
01h 01mWorkshop: Intro to topic modeling using Python
01h 51mNatural Language Processing in Python