Skip to content

elizabethsiegle/analyze-2019-with-tensorflow-twilio-texts

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

6 Commits
 
 
 
 

Repository files navigation

analyze-2019-with-tensorflow-twilio-texts

Presented at the first TensorFlow.js Community Show and Tell and found on the Twilio blog here.

Prerequisites

This uses a TensorFlow.js-provided, pre-trained model trained on a set of 25,000 movie reviews from IMDB, given either a positive or negative sentiment label, and two model architectures to use: CNN or LSTM. This post will be using the CNN.

Replace

process.env.TWILIO_ACCOUNT_SID,
process.env.TWILIO_AUTH_TOKEN

with your Twilio account credentials and then run node sentimentanalysissms.js on the command line to run this file and see how your year went based on text messages sent from your Twilio client/phone numbers. To test the sentiment analysis on any string, you can change

setup().then(function (result) {
  run(result);
});

to

run([]);

Releases

No releases published

Packages

No packages published