diff --git a/cross-reader.tfidf/README.md b/cross-reader.tfidf/README.md
index 6b11e5f..a85965c 100644
--- a/cross-reader.tfidf/README.md
+++ b/cross-reader.tfidf/README.md
@@ -14,6 +14,12 @@
 
     $ pip3 install nltk
 
+You also need to download a nltk package for the tokenizer that is used, to split sentences up in lists of words.
+
+    $ python3
+
+    >>> import nltk
+    >>> nltk.download('punkt')
 
 ## Start