https://github.com/jokoum/sentiment-classification
Multi-layer Perceptron classification of product reviews written in Greek language
https://github.com/jokoum/sentiment-classification
flask machine-learning multilayer-perceptron-network neural-network numpy python sentiment-classification
Last synced: about 2 months ago
JSON representation
Multi-layer Perceptron classification of product reviews written in Greek language
- Host: GitHub
- URL: https://github.com/jokoum/sentiment-classification
- Owner: JoKoum
- Created: 2021-04-04T11:11:15.000Z (about 5 years ago)
- Default Branch: main
- Last Pushed: 2021-04-25T08:55:42.000Z (about 5 years ago)
- Last Synced: 2025-02-26T06:35:45.730Z (over 1 year ago)
- Topics: flask, machine-learning, multilayer-perceptron-network, neural-network, numpy, python, sentiment-classification
- Language: Python
- Homepage:
- Size: 42 KB
- Stars: 0
- Watchers: 1
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# MLP Sentiment classification
The project investigates the performance of the Multi-layer Perceptron algorithm, demonstrated at the [Sentiment Analysis lesson](https://github.com/udacity/deep-learning-v2-pytorch/tree/master/sentiment-analysis-network) from Udacity Deep Learning Nanodegree, when trained with the data from the artificially translated in Greek dataset of the [Machine Learning project](https://github.com/JoKoum/Machine-Learning-Project). Translated reviews are passed to the neural network represented in a simplified bag-of-words model.
The trained neural network is used to predict sentiment of the reviews submitted by users at a web app inderface, using a modified version of the index.html from the ['Deploying a Sentiment Analysis Model' project](https://github.com/JoKoum/Udacity-Deep-Learning/tree/master/AWS) and Flask.