diff --git a/docs/demo/index.rst b/docs/demo/index.rst
new file mode 100644
index 0000000000..f269269827
--- /dev/null
+++ b/docs/demo/index.rst
@@ -0,0 +1,7 @@
+Demos
+=====
+
+.. toctree::
+ :maxdepth: 2
+
+ sentiment
\ No newline at end of file
diff --git a/docs/demo/sentiment.rst b/docs/demo/sentiment.rst
new file mode 100644
index 0000000000..dcec5f356a
--- /dev/null
+++ b/docs/demo/sentiment.rst
@@ -0,0 +1,73 @@
+Sentiment Analysis
+==================
+
+Introduction
+------------
+
+Sentiment Analysis predicts whether an input is positive or negative. The model is based on BERT base, and are trained on the binary classification setting of the Stanford Sentiment Treebank. It achieves about 93.4% accuracy on the dev set.
+
+Demo
+----
+
+You can either input a sentence into the textbox or select one sample from the select control.
+
+.. raw:: html
+
+
+
+
+
+
+
+
+
+ Result will appear here.
+
+
+
\ No newline at end of file
diff --git a/docs/index.rst b/docs/index.rst
index c3d225a957..7b4433fb7a 100644
--- a/docs/index.rst
+++ b/docs/index.rst
@@ -80,4 +80,5 @@ You may find the 60-min Gluon crash course linked from there especially helpful.
examples/index
api/index
website/index
+ demo/index
genindex