https://github.com/xiaohan2012/twitter-sent-dnn
Deep Neural Network for Sentiment Analysis on Twitter
https://github.com/xiaohan2012/twitter-sent-dnn
deep-neural-networks sentiment-analysis theano twitter
Last synced: 16 days ago
JSON representation
Deep Neural Network for Sentiment Analysis on Twitter
- Host: GitHub
- URL: https://github.com/xiaohan2012/twitter-sent-dnn
- Owner: xiaohan2012
- License: mit
- Created: 2015-01-13T11:44:06.000Z (over 10 years ago)
- Default Branch: master
- Last Pushed: 2022-06-21T21:07:28.000Z (almost 3 years ago)
- Last Synced: 2025-04-02T09:17:19.857Z (23 days ago)
- Topics: deep-neural-networks, sentiment-analysis, theano, twitter
- Language: Python
- Size: 18.4 MB
- Stars: 274
- Watchers: 17
- Forks: 87
- Open Issues: 10
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# Twitter Sentiment Analysis using ConvNet
A tool to
- predict sentiment "positiveness" for tweets
## How to use it?
```
>> from sentiment import sentiment_score
>> print sentiment_score(u"I love you")
0.9999
```
It returns a sentiment index ranging from 0 (negative sentiment) to 1 (positive sentiment).
## Online Demo
- predict sentiment "positiveness" for single tweets
- gain an overview of the "positiveness" of [hashtags](https://support.twitter.com/articles/49309-using-hashtags-on-twitter#)
Click [here](https://twitter-sentiment-cnn.herokuapp.com/)
## Algorithm
Please refer to [A Convolutional Neural Network for Modelling Sentences](http://nal.co/papers/Kalchbrenner_DCNN_ACL14) for more information about the algorithm.
## Technical choices
- [Tornado](http://www.tornadoweb.org/en/stable/) as the web framework
- [Theano](http://deeplearning.net/software/theano/) as the neural network training implementation
- [Scipy](http://www.scipy.org/) as the neural network classification(online version) implementation
## Training techniques
1. Fan-in, fan-out initialization
2. Dropout
3. AdaDelta
## Contributors
Han Xiao and Yao Lu