I want extract aspect/nouns related to a adjetive that created a positive or negative sentiment in Sentiment Analysis, but I don’t have a training dataset and my only dataset has 360 comments. How can I do this?

Hi! I'm new to NLP and I've posted here before asking for help. I've read all of the sugestions but I still couldn't solve my problem.

My dataset has 360 reviews from a course that I'm using to extract information. The comments are usually like:
"The course pack is great!" (O material é ótimo)
"Excellent professors!" (Excelente professores)
"Boring because of the maths operations" (Chato por causa das contas de matemática)

When I filter by positive, I want to return "course pack" and "professors". And when I filter by negative, I want it to return "maths operations".

I don't want to reinvent the wheel and create a new algorithm from scratch . I don't have enough time and it's not the main focus of the work I'm doing, I just want to solve this problem. I know R language and a basic of python (but I can understant almost everything that is happening). I've found some codes in python that needs a training base and are mostly for english language. My problem is that I don't have a training base and my language is portuguese.

If anyone can provide me a code, an article, anything that I can run my dataset and find the solution, I'll be extremely grateful.

Submitted November 08, 2020 at 03:55PM by IWantAGoodBattery
via https://ift.tt/3n6Jiy0

Leave a Reply

Fill in your details below or click an icon to log in:

WordPress.com Logo

You are commenting using your WordPress.com account. Log Out /  Change )

Google photo

You are commenting using your Google account. Log Out /  Change )

Twitter picture

You are commenting using your Twitter account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s