Really thorough statistical analysis of your data Its a work in progress with only two steps finished. Not exactly an addon because its in R not Py. So far the project does many little things like find bugs in user’s collection, describe the growth of their collection and text mining. Ultimate goal is to hopefully be able to use anki as continuous cognitive test and allow users to learn about and optimize their memorization process. Instructions to run on your own data : github


It would be really nice to get feedback and user’s examples!

Screen capture of piece of the ‘similar word network graph’ since its not available in notebooks but is generated by the second step. Nodes are decks. Color denotes the final subject decks ended up in. Edges connect two decks that have lots of words in common.

Plot of the history of a single card. Shape is which difficulty was selected at this review. Size is how long thinking took. Color is log time delayed divided by due. Height is how long in days since last review. Horizontal lines denote session and single day. Vertical red lines are ‘states of memory’. Given how badly I have done on this one card, should I still keep trying to learn a foreign language?

1 Like

This is awesome! I wouldn’t say doing bad on a card, or a bunch of cards should influence whether you learn a foreign language, but perhaps performance on specific cards can tell you how well those cards are suited to helping you learn.

I personally made a field in all of my cards for mnemonics, where I put little jokes, stories, or pictures to help me remember specific elements of the cards I am trying to learn. I typically on use them for difficult cards or topics, and they seem to be helping some.

1 Like

That does seem very useful. Next step of the project will be about text mining and should include some measure of effort or ease of each card. Could you give a few examples so that I can figure out how to detect a field for mnemonics?