A probability model for finding hidden topics from document word counts.
LDA is a cafeteria trash detective. It sees wrappers, then guesses pizza day or taco day.
It helps group articles and scan online chatter. First, it gives each text a topic color.
Latent Model
LDA treats each topic as a hidden variable.
PGM
LDA can be drawn as a probability graph of documents, topics, and words.
Unsupervised Learning
LDA finds topics in text without human labels.
Bag-of-Words
LDA usually counts words first with Bag-of-Words.