MuhammedBuyukkinaci/TensorFlow-Sentiment-Analysis-on-Amazon-Reviews-Data

Implementing different RNN models (LSTM,GRU) & Convolution models (Conv1D, Conv2D) on a subset of Amazon Reviews data with TensorFlow on Python 3. A sentiment analysis project.

35
/ 100
Emerging

Leverages pre-trained GloVe embeddings (100D) and compares 13 distinct model variants, including bidirectional architectures and attention mechanisms, with hardware-specific optimizations (CUDNN for GPU, CPU-tuned implementations). Features custom early stopping logic that monitors test loss trends across 80-epoch windows, and combines sequential layers with Conv1D/Conv2D feature extraction for binary sentiment classification on 150k training samples.

No commits in the last 6 months.

No License Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 8 / 25
Maturity 8 / 25
Community 19 / 25

How are scores calculated?

Stars

54

Forks

18

Language

Python

License

Last pushed

Sep 21, 2019

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/nlp/MuhammedBuyukkinaci/TensorFlow-Sentiment-Analysis-on-Amazon-Reviews-Data"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.