diff --git a/similarity.py b/similarity.py
index 087d472..66a3d2b 100644
--- a/similarity.py
+++ b/similarity.py
@@ -1,10 +1,11 @@
 import nltk
 import websearch
-from difflib import SequenceMatcher
 import pandas as pd
+from sklearn.feature_extraction.text import TfidfVectorizer
+from sklearn.metrics.pairwise import cosine_similarity
 
 nltk.download('stopwords')
-nltk.download('punkt')
+nltk.download('punkt_tab')
 stop_words = set(nltk.corpus.stopwords.words('english')) 
 
 def purifyText(string):
@@ -21,9 +22,11 @@ def webVerify(string, results_per_sentence):
             matching_sites.append(url)
 
     return (list(set(matching_sites)))
-
+  
 def similarity(str1, str2):
-    return (SequenceMatcher(None,str1,str2).ratio())*100
+    vectorizer = TfidfVectorizer().fit_transform([str1, str2])
+    vectors = vectorizer.toarray()
+    return cosine_similarity([vectors[0]], [vectors[1]])[0][0] * 100
 
 def report(text):