-
Notifications
You must be signed in to change notification settings - Fork 8
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Decision Trees: The Thread #35
Comments
Hey Jo, sorry it has taken me so long to do this (and I just had a go and it didn't save, so this is a smaller list of what I remember!). It's not just DH, but also thinking about data-driven research, so I'm not sure how relevant it is, but I'd really like to continue our conversation. Also, I think decision-trees is such an interesting way to go - I've come across some useful ones in Social media research and photovoice research in terms of ethical issues etc. Is this the type of decision tree you were thinking of? (obv on a completely different subject!!) chrome-extension://efaidnbmnnnibpcajpcglclefindmkaj/https://journals.sagepub.com/doi/pdf/10.1177/15248399211053892?casa_token=7i9TQyo4Bp8AAAAA:7un0_NthOPNV-SjMJlq2J1mkm78t3V56KBFwBczMZijETzIJIVrZKje2vqPY1g1LkuVx_86SvOw I want to analyse social media data with AI |
I want to measure the environmental impacts of my work (or one aspect of their work) (how can they do this) - carbon calculators etc |
I want to run my algorithm on a GPU (when best to run it in terms of energy etc) |
See the worksheets here https://themuseumsai.network/toolkit/ as a potential model for assisting decision making |
Amazing thanks both. Also thanks Christopher for the suggestion in the meeting: let's start with this as a tool for navigating what is already in the toolkit. "If your need is x, you may be interested in these sections: y, z." |
(1) One big question is the format.
We have said that we don't want anything that will set things in stone - ideally we want the community to be able to keep editing the decision trees.
But it would also be nice to have something quite visual.
For me part of the appeal of a decision tree is browsing around the branches - something you might not get with a quiz if you don't see where each yes/no is leading you.
Suggestions?
(2) What topics do we want to address? Can we brainstorm a lot and then prioritise / decide what's out of scope?
E.g.
I am organising an online event
I am organising a hybrid event
I want to create a website for a research project
I want to create a digital edition of a book
I want to create a personal website
I want to create a website for a research network
I want to do topic modelling
I want to build a recommendations engine
I want to train a classifier
I think my laptop / desktop / device needs replacing
I am writing a data management plan
I am requesting equipment for my DH lab
I think it's time to replace my work computer
What else?
The text was updated successfully, but these errors were encountered: