haoopeng/CNN-yelp-challenge-2016-sentiment-classification
IPython Notebook for training a word-level Convolutional Neural Network model for sentiment classification task on Yelp-Challenge-2016 review dataset.
Implements 1D CNN for both binary and 5-way multi-class sentiment prediction, comparing Keras embedding layers against pre-trained Word2Vec representations (300-dim vectors). The architecture uses convolution-pooling-dense layers with dropout regularization, achieving 77.9% accuracy on binary classification. Includes complete preprocessing pipeline converting raw JSON reviews to fixed-length word sequences via padding/truncation strategies.
112 stars. No commits in the last 6 months.
Stars
112
Forks
48
Language
Jupyter Notebook
License
—
Category
Last pushed
Feb 02, 2020
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/haoopeng/CNN-yelp-challenge-2016-sentiment-classification"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
RubixML/Sentiment
An example project using a feed-forward neural network for text sentiment classification trained...
cmasch/cnn-text-classification
Text classification with Convolution Neural Networks on Yelp, IMDB & sentence polarity dataset v1.0
nas5w/imdb-data
A JSON file of 50,000 IMDB movie reviews to be used in machine learning applications.
SrinidhiRaghavan/AI-Sentiment-Analysis-on-IMDB-Dataset
Sentiment Analysis using Stochastic Gradient Descent on 50,000 Movie Reviews Compiled from the...
VuBacktracking/mamba-text-classification
Text Classification using Mamba Model