diff --git a/README.md b/README.md
index cad6773..50f456c 100644
--- a/README.md
+++ b/README.md
@@ -2,3 +2,4 @@
 Experimental repository aimed at using transformers (such as CovidBERT) and Deep Learning techniques to retrieve and visualize semantic clusters underlying the CORD-19 database.
 
 ![Alt Text](/docs/cord19_semantic_clusters.gif)
+
diff --git a/asreviewcontrib/semantic_clustering/semantic_clustering.py b/asreviewcontrib/semantic_clustering/semantic_clustering.py
new file mode 100644
index 0000000..97d49af
--- /dev/null
+++ b/asreviewcontrib/semantic_clustering/semantic_clustering.py
@@ -0,0 +1,83 @@
+# Copyright 2021 The ASReview Authors. All Rights Reserved.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+# import ASReview
+from tqdm import tqdm
+from asreview.data import ASReviewData
+
+# import numpy
+import numpy as np
+
+# import transformer autotokenizer and automodel
+from transformers import AutoTokenizer, AutoModel
+
+# disable transformer warning
+from transformers import logging
+logging.set_verbosity_error()
+
+# import tqdm
+
+
+def SemanticClustering(asreview_data_object):
+
+    # load data
+    print("Loading data...")
+    data = load_data(asreview_data_object)
+
+    # cut data for testing
+    data = data.iloc[:10, :]
+
+    # load scibert transformer
+    print("Loading scibert transformer...")
+    transformer = 'allenai/scibert_scivocab_uncased'
+
+    # load transformer and tokenizer
+    print("Loading tokenizer and model...")
+    tokenizer = AutoTokenizer.from_pretrained(transformer)
+    model = AutoModel.from_pretrained(transformer)
+
+    # tokenize abstracts and add to data
+    print("Tokenizing abstracts...")
+    data['tokenized'] = data['abstract'].apply(lambda x: tokenizer.encode_plus(
+        x,
+        padding='longest',
+        add_special_tokens=False,
+        return_tensors="pt"))
+
+    # generate embeddings
+    print("Generating embeddings...")
+    data['embeddings'] = data['tokenized'].apply(
+        lambda x: model(**x, output_hidden_states=False)[-1])
+
+    from dim_reduct import run_pca
+    n_components = .98
+    #pca = run_pca(data['embeddings'], n_components)
+
+    print(data['embeddings'][0].detach().numpy())
+
+
+def load_data(asreview_data_object):
+
+    # extract title and abstract, drop empty abstracts and reset index
+    data = asreview_data_object.df[['title', 'abstract']].copy()
+    data['abstract'] = data['abstract'].replace('', np.nan, inplace=False)
+    data.dropna(subset=['abstract'], inplace=True)
+    data = data.reset_index(drop=True)
+
+    return data
+
+
+if __name__ == "__main__":
+    filepath = "https://raw.githubusercontent.com/asreview/systematic-review-datasets/master/datasets/van_de_Schoot_2017/output/van_de_Schoot_2017.csv"
+    SemanticClustering(ASReviewData.from_file(filepath))
diff --git a/docs/semantic_clusters.gif b/docs/semantic_clusters.gif
new file mode 100644
index 0000000..b28701b
Binary files /dev/null and b/docs/semantic_clusters.gif differ