diff --git a/data_processing/README.md b/data_processing/README.md
new file mode 100644
index 0000000000000000000000000000000000000000..3afab164b799b23f2f5c1614110747a5b20d7870
--- /dev/null
+++ b/data_processing/README.md
@@ -0,0 +1,5 @@
+The files are organized into three folders:
+
+1. `data`: Contains all the datasets and raw data files.
+2. `scripts`: Includes all the scripts for data extraction, preprocessing and integration.
+3. `results`: Stores the output files of the processing.
\ No newline at end of file