Deep and Dense Sarcasm Detection

Recent work in automated sarcasm detection has placed a heavy focus on context and meta-data. Whilst certain utterances indeed require background knowledge and commonsense reasoning, previous works have only explored shallow models for capturing the lexical, syntactic and semantic cues present within a text. In this paper, we propose a deep 56 layer network, implemented with dense connectivity to model the isolated utterance and extract richer features therein. We compare our approach against recent state-of-the-art architectures which make considerable use of extrinsic information, and demonstrate competitive results whilst using only the local features of the text. Further, we provide an analysis of the dependency of prior convolution outputs in generating the final feature maps. Finally a case study is presented, supporting that our approach accurately classifies additional uses of clear sarcasm, which a standard CNN misclassifies.