Word2vec use gensim corpus and easy create training modul.
- Use or create data set ( you can use data set from project )
- run source code ClearDataGensim for clear html tag
- run source PreprocessingData with data result from script ClearDataGensim (this for clear stop word )
- run source sentiment analysis with data result from script PreprocessingData ( this for create base file sentiment postive and negative )
- run source TrainingModelPositif (use Positive.txt) and run source TrainingModelNegative ( use Negative.txt ) for get model postive dan negative
- run source CekSmiliarity for cek word from word smiliarity
- run source word2vecvisualization to get visualization vector
use python version 3 to up.
install gensim install nltk install numpy etc
This project is licensed under the MIT License - see the LICENSE.md file for details