diff --git a/spacy/displacy/__init__.py b/spacy/displacy/__init__.py
index b651c0996..d2ef21dbd 100644
--- a/spacy/displacy/__init__.py
+++ b/spacy/displacy/__init__.py
@@ -116,7 +116,7 @@ def parse_deps(orig_doc, options={}):
     doc (Doc): Document do parse.
     RETURNS (dict): Generated dependency parse keyed by words and arcs.
     """
-    doc = Doc(orig_doc.vocab).from_bytes(orig_doc.to_bytes())
+    doc = Doc(orig_doc.vocab).from_bytes(orig_doc.to_bytes(exclude=["user_data"]))
     if not doc.is_parsed:
         user_warning(Warnings.W005)
     if options.get("collapse_phrases", False):
diff --git a/spacy/tests/regression/test_issue3882.py b/spacy/tests/regression/test_issue3882.py
new file mode 100644
index 000000000..1b2dcea25
--- /dev/null
+++ b/spacy/tests/regression/test_issue3882.py
@@ -0,0 +1,15 @@
+# coding: utf8
+from __future__ import unicode_literals
+
+from spacy.displacy import parse_deps
+from spacy.tokens import Doc
+
+
+def test_issue3882(en_vocab):
+    """Test that displaCy doesn't serialize the doc.user_data when making a
+    copy of the Doc.
+    """
+    doc = Doc(en_vocab, words=["Hello", "world"])
+    doc.is_parsed = True
+    doc.user_data["test"] = set()
+    parse_deps(doc)