Multi-view informed attention-based model for Irony and Satire detection in Spanish variants

摘要

Making machines understand language and reasoning on it has been one of the most challenging problems addressed by Artificial Intelligent researchers. This challenge increases when figurative language is used for communicating complex meanings, intentions, emotions and attitudes in creative and funny ways. In fact, sentiment analysis approaches struggle when facing irony, satire and other figurative languages, particularly those where the explanation of a prediction might arguably be as necessary as the prediction itself. This paper describes a new model MvAttLSTM based on deep learning for irony and satire detection in tweets written in distinct Spanish variants. The proposed model is based on an attentive-LSTM informed with three additional views learned from distinct perspectives. We investigate two strategies to pass these views into MvAttLSTM. We perform an extensive evaluation on three corpora, one for irony detection and two for satire detection. Moreover, in order to study the robustness of our proposed model, we investigate its performance on humor recognition. Experiments confirm that the proposed views help our model to improve its performance. Moreover, they show that affective information benefits our model to detect irony and satire. In particular, a first analysis of the results highlights the discriminating power of emotional features obtained from SenticNet and SEL lexicon. Overall, our system achieves the state-of-the-art performance in irony and satire detection in Spanish variants and competitive results in humor recognition.