9 Natural language processing with TensorFlow: Sentiment analysis

 

This chapter covers

  • Preprocessing text with Python
  • Analyzing text-specific attributes important for the model
  • Creating a data pipeline to handle text sequences with TensorFlow
  • Analyzing sentiments with a recurrent deep learning model (LSTM)
  • Training the model on imbalanced product reviews
  • Implementing word embeddings to improve model performance

9.1 What the text? Exploring and processing text

9.2 Getting text ready for the model

9.2.1 Splitting training/validation and testing data

9.2.2 Analyze the vocabulary

9.2.3 Analyzing the sequence length

9.2.4 Text to words and then to numbers with Keras

9.3 Defining an end-to-end NLP pipeline with TensorFlow

9.4 Happy reviews mean happy customers: Sentiment analysis

9.4.1 LSTM Networks

9.4.2 Defining the final model

9.5 Training and evaluating the model

9.6 Injecting semantics with word vectors

9.6.1 Word embeddings

9.6.2 Defining the final model with word embeddings

9.6.3 Training and evaluating the model

Summary

Answers to exercises

sitemap