The sentiment analysis toolkit in stanford corenlp is trained on a sentence-level data set. If you need a document-level sentiment engine, I think training a new model on documents is a better choice. You can also try to process the sentences one by one, and use some tricky methods (such as average, max) as your baselines to test how it works.
Read full article from java - How to get overall sentiment for multiple sentences - Stack Overflow
No comments:
Post a Comment