Some lessons learned using health data literature for smart information retrieval

Big Data paradigm is leading both research and industry effort calling for new approaches in many computer science areas. In this paper, we show how semantic similarity search for natural language texts can be leveraged in biomedical domain by Word Embedding models obtained by word2vec algorithm, exploiting a specifically developed Big Data architecture. We tested our approach using a dataset extracted from the whole PubMed library. Moreover, we describe a user friendly web front-end able to show the usability of this methodology on a real context that allowed us to learn some useful lessons about this peculiar kind of data.