Calculating the similarity of two sentences is very useful to nlp, however, to get better similarity result, many researchers use deep learning to improve the process. In this tutorial, we will use python difflib library to calculate, which is very simple to beginners.
Import library
import difflib
Create a function to calculate the similarity
def string_similar(s1, s2): return difflib.SequenceMatcher(None, s1, s2).quick_ratio()
Create two sentences
s1 = 'i love this book' s2 = 'this book is my favorite'
Calculate the similarity of these two sentences
print (string_similar(s1, s2))
The similarity of these two sentences is: 0.75.