Towards automated visualisation of scientic literature

Nowadays, an exponential growth in biological data has been recorded, including both structured and unstructured data. One of the main computational and scientific challenges in the modern age is to extract useful information from unstructured textual corpora to effectively support the decision making process. Since the emergence of topic modelling, new and interesting approaches to compactly represent the content of a document collection have been proposed. However, the effective exploitation of the proposed strategies requires a lot of expertise. This paper presents a new scalable and exploratory data visualisation engine, named ACE-HEALTH (AutomatiC Exploration of textual collections for HEALTH-care), whose target is to easily analyse medical document collections through the Latent Dirichlet Allocation. To streamline the analytics process and enhance the effectiveness of data and knowledge exploration, a variety of data visualisation techniques have been integrated in the engine to provide navigable informative dashboards without requiring any a-priori knowledge on the analytics techniques. Preliminary results obtained on a real PubMed collection show the effectiveness of ACE-HEALTH in correctly capturing the high-level overview of textual medical collections through innovative visualisation techniques.