Emotion-based cross-variety irony detection

This work is centered on the data made available for the IroSvA challenge, consisting of three variants of Spanish language from three different countries. We propose a simple model for identifying irony, based on tweet embeddings, refraining from using of additional NLP techniques. We aim to find cues that are able to generalize the knowledge obtained from a language variant, and evaluate the ability to detect irony in different combinations of variants, from different countries and topics. For this purpose, we propose using six features based on the degree of emotion present in each tweet. These automatically tagged features include 5 levels of strength, ranging from none to very high, of six emotions: love, joy, surprise, sadness, anger, and fear. Experiments were carried out with different combinations of language variants. Obtained results show that exclusively using the information of the emotion levels (discarding the embeddings) could improve the irony detection in a language variant different from that used for training.