Text Mining and Modelling in R
summary
Slides show text mining in R using tidytext, text2vec, LDABvis, word2vec. Uses Trump tweets as the dataset, discovers an ampersand tokenization bug, builds a document–term matrix and fits LDA with five topics, notes tf‑idf is weak on very short tweets, uses averaged word embeddings to find similar tweets, points out keras via reticulate forces Python and zero‑indexing friction, and highlights pre-trained models like BERT and transfer learning as the best current option.
AI-written summary · about
chapters (9)
- 0:00Start
- 0:33Text mining and modelling in R
- 1:15Counting
- 2:58Weighing
- 4:16Plotting
- 5:20Topic modelling
- 10:10Word Embeddings
- 12:21Text classification
- 13:22Neural Network thoughts
related talks
31mTaking AI/ML to the next level: Text!
35mHow does text become data?
35mLeveraging LLM for text augmentation in Topic Modeling
45mDecoding Topics: A Comparative Analysis of Python’s Leading Topic Modeling Libraries Using Climate C
01h 09mAutomatic Tagging of Short Texts with scikit-learn and NLTK
23mText mining online data with scikit-learn
30mKick-Start your Understanding of Machine Learning with Python
01h 29mTricks, tips and topics in Text Analysis