mratanusarkar / twitter-sentiment-analysis

a demo poc for sentiment analysis of tweets
0 stars 0 forks source link

combine words with varying uppercase or lowercase letters into a single word #10

Open mratanusarkar opened 1 year ago

mratanusarkar commented 1 year ago

The current implementation treats words with different cases (uppercase, lowercase, pascal case, snake case, camel case, title case, etc) as separate words. This is causing the word cloud to be filled with the same types of words, and hampering the frequency count. This could be improvised, by combining similar types of words into one single word.