https://github.com/thevarunsharma/text-sentiment-classification
A web application with Python backend which predicts the sentiment/mood (positive or negative) associated with input text.
https://github.com/thevarunsharma/text-sentiment-classification
deep-learning flask-application keras lstm-neural-networks machine-learning nlp python sentiment-analysis tensorflow
Last synced: about 2 months ago
JSON representation
A web application with Python backend which predicts the sentiment/mood (positive or negative) associated with input text.
- Host: GitHub
- URL: https://github.com/thevarunsharma/text-sentiment-classification
- Owner: thevarunsharma
- Created: 2018-10-09T16:01:50.000Z (over 7 years ago)
- Default Branch: master
- Last Pushed: 2019-02-04T09:22:33.000Z (over 7 years ago)
- Last Synced: 2025-07-04T20:41:20.804Z (12 months ago)
- Topics: deep-learning, flask-application, keras, lstm-neural-networks, machine-learning, nlp, python, sentiment-analysis, tensorflow
- Language: Jupyter Notebook
- Homepage:
- Size: 412 KB
- Stars: 2
- Watchers: 0
- Forks: 2
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Text-Sentiment-Classification
A model for sentiment classification on text (positive or negative), trained and built using keras which uses a RNN with LSTM units. Dataset used was taken from Kaggle: Amazon Reviews for Sentiment Analysis dataset (https://www.kaggle.com/bittlingmayer/amazonreviews), which included 3.6M training examples(2.88M train and 0.72M validation) and 400k test examples. The model achieved test accuracy of 93.6% and training accuracy of 94.6%.
Based on this model created a web-user interface using Flask(Python) for backend, which takes as input a piece of text and returns the corresponding sentiment (positive/negative).