I wrote a simple arXiv quick browser + article suggester in the terminal. I personally use it on a day to day basis and would love suggestions on ways to improve it.
If you're going to be doing ML and require downloads of PDFs, I would recommend getting the bulk data from s3 instead of downloading: https://arxiv.org/help/bulk_data_s3
It's a little more complicated to use, but you get it ALL ;)
In addition to TfIdf, topic modelling would is a very good fit for browsing and finding similar papers. Here is a demo of LDA applied to 10% of the quant-ph arXiv papers that I worked on back in the day: https://www.cs.mcgill.ca/~isavov/arxiv_demo/readme.html
This is very cool, thank you :). I was trying to keep the script lightweight so only wanted articles that I'd already read used for the NLP. In hindsight that may not have been necessary.
The menu doesn't work, it just says "GOODBYE" whenever I try to use it. Some basic in-tool instructions would go a long way here, given this isn't really a CLI tool, it's a menu based console UI tool.
That's true ;), I had to compromise and only show the abstract for now. It does work for me just in terms of skimming through the articles to find what I want to read. I'm looking into adding another layer of menus to show the actual text though.