diff --git a/data-computer/v1/lda.py b/data-computer/v1/lda.py
index 4e732de..6ded96c 100755
--- a/data-computer/v1/lda.py
+++ b/data-computer/v1/lda.py
@@ -69,8 +69,8 @@
 
 
 # training LDA
+texts = []
 for line in all_data:
-    texts = []
     if "value" in line:
         texts.append(tokenize(lemmatize(uniformize(line["value"]))))
     else: