Final project

The final project is the main assignment of the second half of the course. Final projects can be done individually or in groups of 2 people. Group projects are expected to be more substantial than individual ones. All projects are required to be related in a substantive way to at least one of the central topics of the course. The main components are as follows:

  • Project milestone (due April 20, 11:59pm) – a short overview of your project including at least the following information:
    • A statement of the project's goals
    • A summary of previous approaches (i.e., what you have found in the literature)
    • The resources you will use (corpora, lexicons, etc.) and a clear indication of what you may need to do to get them in a form appropriate for your project (e.g., annotate, extract features, render in ARFF, etc.)
    • A summary of your approach (methodology, features used if relevant, etc.)
    • A summary of progress so far: what you have done, what you still need to do, and any obstacles or concerns that might prevent your project from coming to fruition
  • Presentations (May 5 and 10) – We'll use the last sessions of the course for in-class final project presentations. Please use the presentation template provided. If not completed, the presentation should overview the preliminary results and the plan for the final results.
  • Final project (due May 16 ABSOLUTE DEADLINE) – There are two types of papers, each with slightly different requirements:
    • Research papers, which should contain clear sections describing
      • the problem you are addressing;
      • your hypothesis or proposed solution (if you are implementing someone else's solution, where you got the idea from);
      • alternative solutions, including solutions found in the literature and a baseline that you are comparing your solution to;
      • your methodology;
      • your evaluation;
      • some discussion of what your results imply for your hypothesis/problem.
    • Implementation papers, where you do a big semantic data labeling project (or similar). Here you want clear sections describing
      • the data you are labeling;
      • description of and rationale for the annotation scheme used;
      • your methodology (what you did, how you did it, what tools were used etc.);
      • an evaluation of results;
      • a discussion of what you learned.

NOTE: There are numerous resources available for use in these projects, including APIs for gathering and processing Twitter data as well as corpora, lexicons, ontologies, etc. Please consult me for more information!