Rajspeaks / Deep-Learning-Approach-to-Bengali-Text-Visualization-using-Word2Vec-Model

This repository consists of Bengali Text-Visualization using Word2Vec Model. A mini project under the mentorship of Prof. Sandipan Ganguly, HIT-K.

Bengali Text Visualization using Word2Vec Model

This repository consists of Bengali Text-Visualization using Word2Vec Model in two parts. One is applied on the dataset of HISTORY OF BENGAL and another is applied on the dataset of HISTORY BEHIND THE INDEPENDENCE DAY OF INDIA respectively. Data is collected from Wikipedia.

Library requirements:

• Sklearn: Used for data preprocessing, model selection, classification, Regression, clustering.
• Matplotlib: It's used for 2D or 3D plotting to show Histogram, Bar-Chart etc
• Gensim: Open Source Library used in Text Analysis, Word2Vec, Doc2Vec.
• Used Amar Bangla bengali font & sample texts are collected from Wikipedia.

Tools:

• Google Colab/ You can use Jupyter also
• Language: Python
• Wor2Vec from Gensim
• Matploitlib Pyplot

Details:

The text visualization has been done in two parts.

• HISTORY OF BENGAL
• HISTORY BEHIND THE INDEPENDENCE DAY OF INDIA.

© Rajdeep Das