Project – CS 8803 – Visual Data Analysis

Description

This is a semester-long group project where you will do human-centered analysis on different datasets, using different tools/techniques, and present your findings in writing and via a presentation (to the rest of the class). I will facilitate some in-class discussions about project groupings, but you should explore ideas for who you want to work with amongst yourselves as well. I want the teams to be balanced in terms of background and experience.

The group project for this semester will consist of using existing techniques and tools to analyze different datasets for different sensemaking or decision-making tasks. There are 2 parts of the group project. Each will use a different dataset, technique, or tool (described in more detail below). In general, all 3 will consist of your team analyzing a simulated intelligence analysis dataset. It’s like you get to play a detective, and are tasked with “finding something fishy” in the data.

Teams sizes are set to 4. Exceptions are made to allow 5 or 3, but you’ll need instructor approval before doing so. It is important that each team member participates in the group project. If you do not participate, you will receive a lower grade than your teammates. If you have the impression that a team member is slacking off at any time during your project, you should first speak with them to address your concern. If that does not help, please notify the instructor and TA.

Each part of the project will have two components that make up your grade: a results document and a presentation.

Component 1: Results Document: Your team will go through each dataset and “solve” the tasks (i.e., detect suspicious activity in the data, make a decision, etc.). Given the content we talked about in class, your team will prepare a document describing your process. It should include information regarding what structured analytic techniques you used (i.e., what’s you process?), what hypotheses and evidence you found (and discarded), how you worked collaboratively (or individually), how the tools or techniques that you used helped foster sensemaking activities, how you handled cognitive biases, etc. Your team will prepare a document (max 10 pages) that describes your process. This document should contain screenshots, pictures of things you drew on whiteboards (if you did), and information that helps answer the questions above. In general, reading this document should give us an idea of how you analyzed the dataset. The results document should be a pdf uploaded to Canvas (by each team member). This document should include:

Team members (and team name)
List of tools or techniques you used to help you analyze the data
A description of what you found. What is your final decision or action that you would recommend, and why?
Did you find any other insights or patterns that are interesting, but would not recommend? For example, did you consider an alternative but ultimately did not go with it as your final result.
Describe your analytic process or provenance. What steps did you take? What findings were important along the way that helped shape your analysis? Feel free to include photos or screenshots that will help describe this.

Component 2: In-class presentation: For each part of your project, your team will present to your analysis and results to the rest of the class. The presentation should be around 10 minutes long, with around 3 minutes planned for questions. The presentation should answer the overall question for the task in the project part, highlight and summarize your analytic process, and communicate how certain you are with the recommendation/finding. For example, are there alternatives that you considered, but ultimately did not go with (and if so, why)? Be prepared for the instructor, TA, or your classmates to ask you about your process or findings.

Project Parts

(Part 1) Analysis by Hand

To start out with, your team will analyze a relatively small dataset by hand. This involves using a simple text editor, or even printing out the documents and using pens, highlighters, etc. Note that for this part, you are not allowed to use any “analysis” software. The goal of this is to learn about the challenges and nuances of performing data analysis to gain insights and make a decision.

Dataset: The dataset for this part is uploaded to the Files section of Canvas. It is a .zip file with the .txt files and a readme file that details your task.

What to turn in: Each team member should submit the results document (described above), and prepare (and be present) during the in-class presentation.

Grading: You will be evaluated based on the quality of both components (document and presentation). Remember, the goal is to understand that analytic provenance that you performed to get to the decision/finding that you had. Remember that this includes options that you had, explored, but ultimately did not chose. Document your process in terms of the hypotheses, evidence, and supporting images (photos from phones is ok if you did this part by hand).

(Part 2) Intelligence Analysis Using Jigsaw

For this next part of the project, you will use a text analysis tool to help with a larger dataset. It consists of a set of text files, similar to the one used in Part 1.

Dataset: The dataset is already included in the Jigsaw download under the Files section on Canvas. Your task (readme) for this is as follows:

It is Fall of 2004 and one of your analyst colleagues has been called away from her current tasks to an emergency. The boss has given you the assignment of picking up her investigation and completing her task. She has been asked to pursue a line of investigation into some unexpected activities concerning wildlife law enforcement, endangered species issues, and ecoterrorism. This isn’t exactly your specialty area, but your boss believes you are one of the few people who could get to the bottom of whatever is going on. In fact, you would have been given this investigation if you hadn’t been busy on another assignment when your colleague had started.

You do know a few things coming into this effort. First, you were instrumental in cracking those investigations from last year, so issues about mad cow or Alderwood, Washington, are not part of this. Also, you know a little about ecoterrorism and animal rights groups, so, for example, the activities of the People for the Ethical Treatments of Animals (PETA) and Earth Liberation Front (ELF) are not of interest, unless they happen to be tied to some larger, or more pervasive plot.

Analyze the data, report your findings, and ensure your provenance is well documented so as to instill confidence in the team to whom you will report your findings.

Tools: For this part of the project, you will be using Jigsaw, a visual analytics tool for analyzing text data (developed here at Georgia Tech). While we will only briefly cover how to use Jigsaw in class, there are several tutorials available for you to look through.

Getting started: Download the .zip, extract it, and launch Jigsaw. On MacOS, this entails executing the Jigsaw.command file to launch the Java application. From there, navigate to File -> Import -> (Jigsaw Datafiles) -> browse to the /datafiles subfolder and select the Part2 .jig file. On the next entity extraction window, do not change any selection and click Identify. The system will take a moment to parse the data, then return to the main menu. Remember, at this point you can save your workspace at any point. It’s a good idea to do so in case there are crashes or other issues that may cause you to accidentally lose your work.

What to turn in: Each team member should submit the results document (described above), and prepare (and be present) during the in-class presentation.