Final Project Text Mining

Three highly different data sets are employed in this project: a large data set that contains 4187891 spontaneous book reviews, a large data set filled with 53022 well-crafted financial news, and a small data set with 2348 pieces of professional medical transcripts containing much professional jargon. Can we create a classification machine that is as responsive as the hypersensitive princess, who could recognise that there is one pea in her bed, despite many layers of exquisite mattresses.