I pull text data using Twitter API with keyword 'PPKM'.
- Getting Data from Twitter with Tweepy
- Preprocessing Text : drop duplicate text, remove(emoticon,punctuation,stopwords),spell checking
- Create some visualization(Word cloud,n-gram) to got some insight
- converting text data using TFidf vectoriezer
- Clustering text data and create visualization for elbow method
- choose the best n_cluster and analyze again with KMeans
[1] Python Sastrawi. URL : https://github.com/har07/PySastrawi