diff --git a/src/data/make_dataset.py b/src/data/make_dataset.py
index ca68273..4aebd0b 100644
--- a/src/data/make_dataset.py
+++ b/src/data/make_dataset.py
@@ -22,7 +22,7 @@ def main(input_filepath, output_filepath):
                                   'given_names', 'family_name', 'biography', 'other_names', 'urls', 
                                   'primary_email', 'other_emails', 'keywords', 'external_ids', 'education', 
                                   'employment', 'n_works', 'works_source', 'activation_date', 'last_update_date',
-                                   'n_doi', 'n_arxiv', 'n_pmc', 'n_other_pids'])
+                                   'n_doi', 'n_arxiv', 'n_pmc', 'n_other_pids'], encode = 'utf-8')
     
     logger.info('Loading list columns')
     logger.info('... other_names')