Context The cleaned dataset was created to purpose contextual analysis for COVID-19 Open Research Dataset Challenge. The file includes only important columns what useable to contextual clustering. Content **COVID-19-ORDC-cleaned-metadata.xlsx** Dataset consits of 10 columns. There are 4 columns for document identification: - cord_uid - sha - journal - authors There are 6 columns purpose for NLP contextual analysis: - title - abstract - common_words - vectors - clusters - words_of_topic_in_clusters **vecs.tsv** Content of vecs.tsv is all vectors from car. The file can used in embedding projector. **meta.tsv** The meta.tsv contains the meta data to vecs.tsv. There ara 3 columns. - title: title of documents - clusters: cluster's number of document - words of topic: Topic words for clusters generated by LDA analysis.