I have a set of reviews for which I need to extract their sentiments and use those sentiments as an independent variable in an econometric model. I used one of the ready-to-use models of hugging face that was trained on a domain similar to my dataset, leading to better sentiment labels for my reviews than using lexicons. However, I am not sure about the validity of this approach.

Is this approach valid? Is there any name for it? Could you provide me with any papers that took a similar approach?



Your Answer

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