Project Title

DSC160 Data Science and the Arts - Midterm Project Repository - Spring 2020

Project Team Members:

• Firstname Lastname1, [email protected]
• Firstname Lastname2, [email protected]
• Firstname Lastname3, [email protected]
• Firstname Lastname4, [email protected]
• Firstname Lastname5, [email protected]

Abstract

(10 points)

For the project proposal, please write a short abstact addressing the questions below. You should replace the entire contents of this section with one to two paragraphs addressing the following:

• What is the data set that you are going to analyze?
• What is your research question?
• What is your hypothesis about the results?
• What features of the data will you use to address your question?
• What techniques and software tools will you use to extract these features?
• What analytic techniques will you use?
• What forms will your results take? (graphs, charts, images, sonification, Wordles, etc)
• How are you expanding on topics we have covered in class?
• Why is it interesting? (personally, culturally, politically, other)

Data

(10 points)

This section will describe your data and its origins. Each item should contain a name of the data source, a link to the source, and any necessary background information such as:

• What is your cultural data source?
• When was it made?
• Who created the works?
• Is it digital native, or is it some kind of scan, recording, photo, etc., of an analog form?

Code

(20 points)

This section will link to the various code for your project (stored within this repository). Your code should be executable on datahub, should we choose to replicate your result. This includes code for:

• data acquisition/scraping
• cleaning
• analysis
• generating results.

Link each of your notebooks or .py files within this section, and provide a brief explanation of what the code does. Reading this section we should have a sense of how to run your code.

Results

(30 points)

This section will contain links to documentation of your results. This can include figures, sound files, videos, bitmaps, as appropriate to your domain of analysis. Each result should include a brief textual description, and all should be listed below:

• image files (.jpg, .png or whatever else is appropriate)
• audio files (.wav, .mp3)
• written text as .pdf

Discussion

(30 points, three to five paragraphs)

The first paragraph should be a short summary describing your results.

The subsequent paragraphs could address questions including:

• Why is this culturally relevant?
• How does your computational approach differ from the traditional art historical, musicological, manuel/subjective approach to analyzing your cultural subject?
• How do you think the original artists/musicians would respond to this type of analysis? Would it change/inform their practice in some way?
• How do your results relate to broader social, cultural, economic political, etc., issues?
• In what future directions could you expand this work?

Team Roles

Provide an account of individual members and their efforts/contributions to the specific tasks you accomplished.

Technical Notes and Dependencies

Any implementation details or notes we need to repeat your work.

• Additional libraries you are using for this project
• Does this code require other pip packages, software, etc?
• Does this code need to run on some other (non-datahub) platform? (CoLab, etc.)

Reference

References to any papers, techniques, repositories you used:

• Papers
• Repositories
• Blog posts