Mining Twitter for Fine-Grained Political Opinion Polarity Classification, Ideology Detection and Sarcasm Detection
Sandeepa Kannangara · 2018
In this paper, we propose three models for socio-political opinion polarity classification of microblog posts. Firstly, a novel probabilistic model, Joint-Entity-Sentiment-Topic (JEST) model, which captures opinions as a combination of the target entity, sentiment and topic, will be proposed. Secondly, a model for ideology detection called JEST-Ideology will be proposed to identify an individual»s orientation towards topics/issues and target entities by extending the proposed opinion polarity classification framework. Finally, we propose a novel method to accurately detect sarcastic opinions by utilizing detected fine-grained opinion and ideology.