wangz10 / text-classification

A presentation/tutorial on text classification from the basics to advanced.

Introduction to Text Classification

Zichen Wang

Overview of this presentation/tutorial

1. Prepare some data (0_prepare_data)
2. Natural Language Processing Basics
3. Text Classification
   • Applications
   • Defination
   • Methods
     1. Bag-of-words
     2. LSA
     3. Word2vec and Text embedding (Word2Vec)
     4. Paragraph vector (Doc2Vec)
     5. Recurent Neural Network (RNN)

Requrirements

To run the notebooks, install modules on Python2.7 in requirements.txt.

pip install -r requirements.txt

Tensorflow implementation of Word2Vec is available here.