To pass the course, you are required to demonstrate grasp of actual digital humanities work. Therefore, you are tasked with taking some dataset, and processing it in some way to yield an analysis that tackles a question of interest in the humanities.
This assignment requires applying all the knowledge you have learned on the course to devise and test a process going from data to results. To do this, you will need to navigate between the limits of the data, methods and research questions, trying to figure out which line of research is possible. Often, this is an iterative process, starting from something, running up against limits of either data or methodology, and then trying to sidestep those. The most important learning goal of this assignment is to gain experience in this process in practice by going through it.
Potential datasets/APIs are for example (but instead of these please choose a dataset that is relevant to yourself):
We also have a set of automatic transcriptions from 35,000 Finnish language TV and radio programs courtesy of the Finnish public broadcaster YLE available by asking
Tools for processing and analysis are for example:
To return the assignment, you will need to upload your data, code and results into a GitHub repository, link that repository with Zenodo and give us the Zenodo DOI for your work. Include in your repository a document (e.g. a README.md) describing what you've done, following as best as possible the guidelines for open, reproducible research. Make sure the document answers the following questions:
What are your humanities research questions?
Which data did you use?
What did you do to the data (and how can I reproduce it)?
What does the analysis show, how does it answer the humanities research question?
Critically analyse your own pipeline for potential bias and problems. What would still need to be done for the analysis to be trustable?
Further info: as said, the most important learning goal for this assignment is to learn how to navigate the between the shoals of data, method and questions in designing a computational humanities research process. Thus, for submissions, I prefer full pipelines that go from raw data to results. To get there, it is okay to cut massive corners as long as you know which those corners are (and that is what question 5 is for). However, sometimes this just isn't possible. Therefore, submissions can also be just some steps towards a complete pipeline (e.g. the data cleaning part). However, if you don't have end results, you need to very explicitly describe what your next steps would be to get those (i.e. a plan for future research).
To return your assignment, send the Zenodo DOI to Eetu on Slack, along with your student ID number. You probably wont want to include the ID number in the project files themselves, as all of those are public in perpetuity. Remember to also fill the course feedback form!
To further aid you in your work, here are some previous submissions for inspiration (for most of them, you should actually click the GitHub link on the right to start to make sense of them):
Themes in Hungarian folk love songs - DOI: 10.5281/zenodo.44570
Extracting and visualizing biographical information from an old bank matricle - DOI: 10.5281/zenodo.225890
Analysis of a survey on user involvement in software development - DOI: 10.5281/zenodo.237727
Polite vs casual address form use by Finnish language learners in different situations - DOI: 10.5281/zenodo.218844
Discovering patterns in chalcolithic and early bronze age burials in northeast England- DOI: 10.5281/zenodo.215932
Themes discussed in Helsingin Sanomat in 1905 - DOI: 10.5281/zenodo.44572
Differences in use between the words maahanmuuttaja and pakolainen in Finnish newspapers 1970- to present - DOI: 10.5281/zenodo.44544
Differences in how frequently Finnish and Swedish newspapers talk about the Romani people - DOI: 10.5281/zenodo.44590
Contrasting Beck's lyrics to blues lyrics - DOI: 10.5281/zenodo.215292
Extracting and analysing recipe information in an old cookbook - DOI: 10.5281/zenodo.216232
Comparing the use of polite plural "you" in Mandarin Chinese and Lithuanian - DOI: 10.5281/zenodo.1134294
A thematic analysis of the discussion around Guggenheim on the Suomi24 forum - DOI: 10.5281/zenodo.217719
Sentiment analysis of Twitter discussion related to the Indian biometric identifier system Aadhaar - DOI: 10.5281/zenodo.1134623
Differences in language between texts dealing with altered states of mind and normal fiction - DOI: 10.5281/zenodo.230676
Exploring ways to compare adaptations of a literary work - DOI: 10.5281/zenodo.1127754
Preliminary analysis comparing different Finnish cabinet strategies against each other - DOI: 10.5281/zenodo.216604
Preliminary analysis of patterns in the holdings of the Finnish National Gallery - DOI: 10.5281/zenodo.218735