The methodology used is as follows:
- Retrieve the data from twitter regarding a particular topic
- Perform the pre-processing steps on the text data, which involves removing of URLs, typecasting, removing stop words etc.
- Create a term-document matrix to visualize the counts of words.
- Create a word cloud of the words to represent the dominance of words
- Use different libraries in R to perform sentiment analysis on the tweets
- Rate the tweets on 10 emotional polarities and represent in the form of a Histogram
I have taken a lot of inspiration and code from https://www.youtube.com/channel/UCuWECsa_za4gm7B3TLgeV_A :)