https://github.com/nicolay-r/tone-classifier
Application of SVM classifier and NN classifiers for sentiment classification of Russian Twitter messages
https://github.com/nicolay-r/tone-classifier
keras lexicon lstm rnn sentiment-classification sentirueval svm-model theano
Last synced: about 2 months ago
JSON representation
Application of SVM classifier and NN classifiers for sentiment classification of Russian Twitter messages
- Host: GitHub
- URL: https://github.com/nicolay-r/tone-classifier
- Owner: nicolay-r
- License: mit
- Created: 2016-03-17T19:38:49.000Z (over 9 years ago)
- Default Branch: master
- Last Pushed: 2024-06-18T13:38:03.000Z (over 1 year ago)
- Last Synced: 2024-06-18T16:20:44.925Z (over 1 year ago)
- Topics: keras, lexicon, lstm, rnn, sentiment-classification, sentirueval, svm-model, theano
- Language: Python
- Homepage: https://github.com/nicolay-r/tone-classifier/raw/master/doc/aidt_2017.pdf
- Size: 51.2 MB
- Stars: 4
- Watchers: 8
- Forks: 2
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
README
# Lexicon Integration with Machine Learning for Sentiment Analysis
This project represent a code for paper
*[Methods of Lexicon Integration with Machine Learning for Sentiment Analysis System](
https://github.com/nicolay-r/tone-classifier/raw/master/doc/aidt_2017.pdf)*
and describes the application of `SVM` classifier and `Neural Networks`
classifiers for sentiment classification of Russian Twitter messages in the
banking and telecommunications domains of **SentiRuEval-2016** competition.
## Installation
All dependencies described in `Makefile` and could be installed as follows:
```bash
make install
```
## Usage
For research purposes. Use `run/Makefile` to run workflow for
certain task (`bank` or `tcc`) and classifier (`svm`, `lr`), for example:
```bash
cd run && make svm_sre15_bank_w2v_bal
```
returns F-macro/micro result for SentiRuEval-2015 bank dataset using
w2v-based embedding model for balanced test collection.
All embedding classifier settings presented in `data/embedding` folder.
## Resources
* [SentiRuEval-2015] contest data;
* [SentiRuEval-2016] contest data & results of this approach (participant #1) in
comparation with the other participants.
## Papers
This work has been formed into [AIDT Journal 2017/2] paper publication.
The latter was presented at RUSSIR conference in a form of the following posters:
[RUSSIR-2017][Russir-2017 poster], [RUSSIR-2016][Russir-2016 poster];
Early publication could be found here: [Dialog-2016][Dialog-2016 article];
## How to cite
```bibtex
@article{rusnachenko2017methods,
title={Методы интеграции лексиконов в машинное обучение для систем анализа тональности},
author={Русначенко, Николай Леонидович and Лукашевич, Наталья Валентиновна},
journal={Искусственный интеллект и принятие решений},
number={2},
pages={78--89},
year={2017},
publisher={Федеральное государственное учреждение" Федеральный исследовательский центр~…}
}
```
[Russir-2017 poster]: doc/russir_2017_poster.pdf
[AIDT Journal 2017/2]: doc/aidt_2017.pdf
[Russir-2016 poster]: doc/russir_2016_poster.pdf
[SentiRuEval-2016]: https://drive.google.com/drive/u/0/folders/0BxlA8wH3PTUfV1F1UTBwVTJPd3c
[Dialog-2016 article]: http://www.dialog-21.ru/media/3469/rusnachenko.pdf
[SentiRuEval-2015]: http://goo.gl/qHeAVo