Purpose The current paper aims at exploring negative aspects in reviews about Airbnb listings Athens, Greece. Design/methodology/approach aspect-based sentiment approach (ABSA), a subset of analysis, is used. study analyzed 8,200 reviews, which had least one aspect. Based on dependency parsing, noun phrases were extracted, and the underlying grammar relationships used to identify aspect terms. ...

The state-of-the-art approaches to targeted aspect-based sentiment analysis (TABSA) are mostly built on deep neural networks with attention mechanisms. One problem is that embeddings of targets and aspects either pre-trained from large external corpora or randomly initialized. We argue affective commonsense knowledge words indicative could be used learn better target aspect embeddings. therefor...