Since it looks for similar word usage, false positives seem to appear more often when specific topics are talked about, like stocks or crypto.

Does this ignore stop words? Or do all words have the same weighting? I wonder if only focusing on stop words would give a more accurate measure. Maybe we are more comfortable with certain stop words more than others?

https://en.wikipedia.org/wiki/Stop_words

"Stop words are the words in a stop list (or stoplist or negative dictionary) which are filtered out (i.e. stopped) before or after processing of natural language data (text) because they are insignificant."