It is nice to hear from you after a long time! SentiTrack might be using comments in its analysis. I rechecked the results for the article and the results turned out to be much different.
It is nice to hear from you after a long time! SentiTrack might be using comments in its analysis. I rechecked the results for the article and the results turned out to be much different.
They are using a fine tuned roberta model and emotional analysis. The first step is to fetch/scrap the content and analysis. Perhaps the model is returning different values each time. I am not too familiar with LLMs but I think not 2 results for the same input are unique and thus these variations.