Yes, its called graph-api.
You should be aware that scraping data from facebook not using this api its
violation of the regulations of fb laws and could you be ended with ban. So be careful.
I don't think that's a very good idea: the goal is not to make the model predict a more extreme polarity when the tweet relates to the company.
Instead you might want to consider oversampling the few instances of this specific company. For instance if you have 100 company-specific tweets and 1000 general tweets in your training set, you could duplicate the ...
One option is to reframe it as a word embedding problem. Emojis can be embedded in a vector space along with comments and hashtags. Then distance measures and clustering can be used to find the emojis that are associated with different sentiments.