Data analysis for Understanding Healthcare Education Innovations

Abstract

In Natural Language Processing field, mining texts to extract valuable information from unstructured texts is a crucial task. Starting from pre-processing techniques until methods helping to obtain results such as information extraction or retrieval, categorization, clustering and summarization. The aim of this project is that using some of these techniques to identify some hidden topics and clusters to understand one very important segments of society, medical students. Therefore, a corpus of textual data collected by Health Education England was given to achieve this goal. Experiments were conducted and some results produced in terms of topics exploration and positive or negative clusters that could help to develop learning environment