Characterizing Diseases from Unstructured Text: A Vocabulary Driven Word2vec Approach
This work addresses the need for automated disease surveillance tools for public health researchers, though it is incremental as it builds on existing word2vec techniques.
The authors tackled the problem of constructing disease taxonomies from unstructured text like news articles, which typically requires human supervision, by proposing Dis2Vec, a vocabulary-driven word2vec model that automatically creates taxonomies and outperforms state-of-the-art methods in capturing taxonomical attributes across disease classes.
Traditional disease surveillance can be augmented with a wide variety of real-time sources such as, news and social media. However, these sources are in general unstructured and, construction of surveillance tools such as taxonomical correlations and trace mapping involves considerable human supervision. In this paper, we motivate a disease vocabulary driven word2vec model (Dis2Vec) to model diseases and constituent attributes as word embeddings from the HealthMap news corpus. We use these word embeddings to automatically create disease taxonomies and evaluate our model against corresponding human annotated taxonomies. We compare our model accuracies against several state-of-the art word2vec methods. Our results demonstrate that Dis2Vec outperforms traditional distributed vector representations in its ability to faithfully capture taxonomical attributes across different class of diseases such as endemic, emerging and rare.