I'm mining raw Facebook comments (irrelevant) and i am looking for an algorithm that can classify their context as negative/positive/neutral. So you can think of the output in the form of two columns. First column the comment (exists), and second column its classification. If possible i'd like for the algorithm to be able to process the sentence as is (e.g. not having to remove stop words etc). Can someone recommend any resources that i can refer to? I have no problem doing this in either Python or R. Thanks
So, I believe what this question is asking for literature around sentiment analysis of Facebook comments (positive/neutral/negative) sentiment.
There is quite a good paper on this using an encoder-decoder architecture here: https://www.aclweb.org/anthology/Q18-1002/
I would look into Python's spaCy for sentiment analysis. You might also find useful this link https://notebooks.quantumstat.com/