The unbearable hurtfulness of sarcasm

Abstract

In the last decade, the need to detect automatically irony to correctly recognize the sentiment and hate speech involved in online texts increased the investigation on humorous figures of speech in NLP. The slight boundaries among various types of irony lead to think of irony as a linguistic phenomenon that covers sarcasm, satire, humor and parody joined by their trend to create a secondary or opposite meaning to the literal one expressed in the message. Although this commonality, in literature sarcasm is defined as a type of irony more aggressive with the intent to mock or scorn a victim without excluding the possibility to amuse. The aggressive tone and the intent of contempt suggest that sarcasm involves some peculiarities that make it a suitable type of irony to disguise negative messages. To investigate these peculiarities of sarcasm, we examined the dataset of the IronITA shared task. It consists of Italian tweets about controversial social issues, such as immigration, politics and other more general topics. Each tweet is annotated as ironic and non-ironic, and, at a deeper level, as sarcastic and non-sarcastic. Qualitative and quantitative analyses of the dataset showed how sarcasm tends to be expressed with hurtful language revealing the aggressive intention with which the author targets the victim. While irony is characterized by being offensive in hateful context and, in general, moved by negative emotions. For a better understanding of the impact of hurtful and affective language on the detection of irony and sarcasm, we proposed a transformer-based system, called AlBERToIS, combining pre-trained AlBERTo model with linguistic features. This approach obtained the best performances on irony and sarcasm detection on the IronITA dataset.