作者: Mauro Dragoni , Giulio Petrucci
DOI: 10.1109/TAFFC.2017.2717879
关键词: Domain (software engineering) 、 Artificial intelligence 、 Natural language processing 、 Sentiment analysis 、 Deep learning 、 Inference 、 Context (language use) 、 Computer science 、 Word (computer architecture) 、 Artificial neural network 、 Set (abstract data type)
摘要: Multi-domain sentiment analysis consists in estimating the polarity of a given text by exploiting domain-specific information. One of the main issues common to the approaches …