I want to perform a sentiment analysis of a dataset of (Spanish) tweets about COVID-19 vaccines.

I've already scraped the tweets and identified a pretrained model I can use for Spanish.

What I don't really understand - and don't seem to find the right resources either - is
what steps are involved in the whole process?

I know I have to fine-tune the model which I'm not exactly sure how to do.
Do I necessarily need a labeled dataset for this or can I just train the model on my scraped tweets (that don't have a label yet)?

  • $\begingroup$ The pretrained model you linked does not work (at least not directly) for sentiment analysis since it is specifically for question answering. $\endgroup$
    – Oxbowerce
    Sep 11, 2021 at 14:25
  • $\begingroup$ Thanks for the info. I just corrected it. $\endgroup$
    – LeLuc
    Sep 11, 2021 at 21:33


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.