This course requires completion of an individual project that implements the methods presented in the class. The intent of the project is to apply one or multiple concepts learned within the class to an actual data set in order to perform knowledge discovery. The project must be approved by Dr. Boehmke or LTC Smith NLT Friday, 6 October 2017. Students may use an application within their thesis project for work within this class. The real world data set must be something with text, and can be either pre-formatted or something in textual form. At a bare minimum, the text should include more than 5,000 words and should be in English. While these requirements are minimums, the intent is that the problem is analyzed according to the concepts presented in this course and that the results are articulated in a clear manner.
This research project is worth 60% of your total grade for this class. You will provide three deliverables.
Project Written Report – Due Friday, 8 December (35 pts) - For this part of the project assignment, provide a written report describing your analysis of your text and how it informs on the problem laid out in your project proposal. Focus on insights, trends and analysis. This is where you are allowed to put the work you’ve done, but remember this document should flow. This document (not including appendices) should be no longer than 20 pages (single spaced), with any charts/graphs relevant to the discussion imbedded and referenced in the body of the document. Bulky or large figures or charts and examples of your code should be put into the appendix(cies). The format of the report should have at least the following headings: Executive summary (1 pg or less), Background, Problem Frame (ending with the statement of the problem), Data Description and analysis, Findings and Conclusions.
Final Project Presentation – Presentation 27 Nov – 6 December (depending upon sign up), Due Thursday, 7 November (20 pts) - For this part of the project assignment, present your full analysis to the class. The presentation should include a presentation you could give to a sponsor of research and should include at a minimum: Background, Assumptions, Methodology, Analysis, Conclusion/Future Work. The presentation should be no longer than 30 minutes. Aim for 25 minutes, leaving 5 minutes for questions. The content of the presentation should be organized such that it achieves three objectives:
Your attentiveness and professionalism when your classmates present will also play into the grade for your presentation. Note that the slides and write up are not due until after presentations are complete. You are expected to use comments in class to improve your final product before turning in your project.