diff --git a/Source Code/HDT.py b/Source Code/HDT.py
index 7afd1b0..39c9a8e 100644
--- a/Source Code/HDT.py	
+++ b/Source Code/HDT.py	
@@ -29,7 +29,9 @@ def update_pvs(word, pv, id, word_count_dict, word_pv_dict, min_pv_dict, max_pv_
 articlepv = list()
 sum_pv = 0
 ID = 0
-in_file = open("HDTdata4.txt", "r")
+in_file = open("HDTdata4.txt", "r", encoding="latin-1")  # Specify the correct encoding
+
+
 
 for line in in_file:
     if ID == 0: # excluding first line as it is header