Milestone II MADS

MADS SIADS 695 Milestone II

Supervised and Unsupervised Learning

The project component of Milestone II is designed to provide a comprehensive synthesis and assessment of the core data analytics skills that we've gained so far, including, for example, an end-to-end machine learning process applied to a challenging prediction problem; This includes the steps in a typical end-to-end solution path for an interesting problem, including: analysis, implementation, evaluation, and communication of the problem and results, applied to more advanced/specialized problems. The dataset used for this project is a text difficulty dataset from Wikipedia.

Motivation

When the difficulty level of text is perceived as too high, it may prevent many people from reading and learning from that text. So even though there is an abundance of information online, if this information is not provided in an easily digestible format, it will be inaccessible to many audience members. This could have huge consquences in various situations, for example, readers avoiding difficult news stories and instead seeking out easier texts which might not be as high quality. Having high text difficulty could also marginalize non-native English speakers and others with lower reading ability.