We usually don't like going to the dentist. Using common sense to detect irony on Twitter

Abstract

While common sense and connotative knowledge come natural to most people, computers still struggle to perform well on tasks for which such extra-textual information is required. Automatic approaches to sentiment analysis and irony detection have revealed that the lack of such world knowledge undermines classification performance. In this paper, we therefore address the challenge of modelling implicit or prototypical sentiment in the framework of automatic irony detection. Starting from manually annotated connoted situation phrases (e.g. ‘flight delays’, “sitting the whole day at the doctor’s officeâ€), we defined the implicit sentiment held towards such situations automatically by using both a lexico-semantic knowledge base and a data-driven method. We further investigate how such implicit sentiment information affects irony detection by assessing a state-of-the-art irony classifier before and after it is informed with implicit sentiment information.