CASCADE: Contextual Sarcasm Detection in Online Discussion Forums

Understand

The literature in automated sarcasm detection has mainly focused on lexical, syntactic and semantic-level analysis of text.

• However, a sarcastic sentence can be expressed with contextual presumptions, background and commonsense knowledge.
• In this paper, we propose CASCADE (a ContextuAl SarCasm DEtector) that adopts a hybrid approach of both content and context-driven modeling for sarcasm detection in online social media discussions.
• For the latter, CASCADE aims at extracting contextual information from the discourse of a discussion thread.