shivamsingh96-zz/Natural_Language_Processing

Working with text is generally more challenging than working with numerical data. Hence, any kind of technique that helps in generating an intuition of the existing dataset is welcome. One of the simplest approach to understand any text document or to compare multiple documents can be to compute a frequency table of individual words present in the document/documents and use it to conduct further experiements like: finding top words per document, finding top common words among documents etc. In our case, we have taken the challenge of Analyzing Sentiments from Twitter data, so we will focus on how to generate word frequencies and use it to create Word Clouds in Python that will help us get a better overall understanding of the dataset.

Jupyter Notebook