1. How to find an article by an ID:
– just use the search interface, and type in the ID.
2. How to export the data of a particular group:
– just use “export” link to dump the data.
3. What is the dataset format this site provided: about 30MB data,
in this, each row represents [paper_ID, user_hash_name, upload_time,
a_tag_on_the_paper]. If someone have a paper with n tags, then
it have n tuples in this dataset.
4. Problems I faced: how to calculate the item vectors which are composed
of tuples of tags ? Because it’s difficult to differentiate the same paper
from the various ID#, I would like to retrieve the data from the smaller
group by hand.