Hey everyone,

Recently, I’ve found myself bogged down in sending off resumes that seem to never to be read by anyone other than myself.

I’ll go through the whole gamut of picking keywords that match the job description, showcasing my previous experiences, projects, skills etc… But it just seems to never result in a call-back or even an email to tell me I wasn’t selected.

Given that I’m tired of screaming into the hills and hearing it echo back, I want to write a program that streamlines this whole process. I have a couple of resume templates written in TeX script that I can populate with content. Alongside this, I have all of my relevant bullet points in assorted text files labeled appropriately.

The idea would be to feed the program the job description, relevant qualifications, and other miscellaneous text files. These would be processed to give an idea on how my resume should be modified to suit their requirements. Perhaps that could aid in creating a strong resume in a more streamlined fashion. I have no clue what metric should be used to quantify how “good” it is, so that’s to be figured out as well.

I saw “nltk” and “spaCy” are two NLP libraries for Python, but I wanted to open up discussion for those of you who have worked on projects similar to this. I have read mixed comments about the two. Which one seems better suited for this task?

Obviously I’ll review the resume before I submit it, but I want to see if I could get something like this working.

I’m a giant noob when it comes to NLP, but have used Python for the past couple of years for data-science applications. I’d be open to learning a different language if there is a library that has some of these functions already coded, but I’m not a developer.

Thanks for any help! I love the community over here on Lemmy. Many of you have been very helpful and encouraging and it makes me want to keep learning more :)