Skip to content

Commit 2b69677

Browse files
committed
Initial commit
0 parents  commit 2b69677

File tree

2 files changed

+98468
-0
lines changed

2 files changed

+98468
-0
lines changed

README.md

Lines changed: 15 additions & 0 deletions
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,15 @@
1+
# RuReviews: An Automatically Annotated Sentiment Analysis Dataset for Product Reviews in Russian
2+
3+
## Overview
4+
This repository contains an automatically collected dataset for sentiment analysis of product reviews in Russian.
5+
6+
### Pre-trained Word Embeddings
7+
The sentiment classification model was trained on the top of pre-trained Word2Vec embeddings. Texts were pre-processed by [Ekphrasis](https://github.com/cbaziotis/ekphrasis) toll, which helps to perform spell correction, word normalization and segmentation and allows to specify which tokens should be omitted, normalized or annotated with special tags.
8+
9+
**Pre-trained 300 dimensional embeddings may be downloaded at the following link: [rer.300d.txt](https://yadi.sk/d/CwxIRiOZo-ss4A)**.
10+
11+
### Documentation and How to report bugs
12+
* Keras documentation: [https://keras.io/documentation/](https://keras.io/documentation/).
13+
* Ekphrasis documentation: [https://github.com/cbaziotis/ekphrasis](https://github.com/cbaziotis/ekphrasis).
14+
* Scikit-learn documentation: [http://scikit-learn.org/stable/documentation.html](http://scikit-learn.org/stable/documentation.html).
15+
* If you find any issues, please open a bug here on GitHub.

0 commit comments

Comments
 (0)