jack960317 / sentiment-analysis-via-gcn

Chinese text sentiment analysis via Graph Convolution Neural Networks

Sentiment-Analysis-via-GCN

Chinese text sentiment analysis via Graph Convolution Neural Networks

This is the code for Fine-Grained Emotion Classification of Chinese Microblogs Based on Graph Convolution Networks. World Wide Web Journal, Yuni Lai, Linfeng Zhang, Donghong Han, Rui Zhou, Guoren Wang.

---

Requirements

Pytorch >=0.4.0
Numpy
Pandas
Sklearn

We highly recommend you to use anaconda for running these codes.

---

Run the codes

python train_binary_classification.py # for binary emotion classification
python train_fine_grained_classification.py # for fine-grained classification

---

Download the Data

You can download the processed data from Baidu Drive from here. (password=3kxy)

We will upload them on Google Drive soon.