A deep learning approach that detects sentiment using LSTM, word embeddings and keras.


Sentiment Detection for IMDB Ratings with word embedding

  • What is the purpose of this POC: This example show how to train a very good sentiment detection classifier with deep learning, word embedding and keras.

Link to DEMO or 30s VIDEO of the project


  • What is the benefit for the customer: The customer can have an automatic classification of tweets or product reviews, which might help him.
  • What is the benefit for the business: The business owner can moderate


  • How much MD did you use to build it: 3MD including blog post


  • Which data is it based on: IMDB reviews, which have been manually preclassified into positive and negative

Used Technologies

  • Which technologies were used: Keras, Deep learning


  • Which things could be build with this POC if you had more time: It can be used for moderation of user generated content.