diff --git a/data-computer/v1/lda.py b/data-computer/v1/lda.py
index 6ded96c..7c6e39e 100755
--- a/data-computer/v1/lda.py
+++ b/data-computer/v1/lda.py
@@ -27,10 +27,9 @@
     text = remove_accents(text)
 
     # remove punctuation except " ' "
-    punctuation = ''.join(char for char in string.punctuation if char != "'")
-    text = ''.join(char for char in text if char not in punctuation)
+    text = ''.join(char if char.isalpha() or char == "'" else ' ' for char in text)
 
-    return text.lower()
+    return ' '.join(text.lower().split())
 
 #lemmatize
 def lemmatize(text):