Is this Tweet Satirical? A Computational Approach for Satire Detection in Spanish

Resumen

Computational approaches to figurative language have become recently a relevant topic in Computational Linguistic. We focus on the study of satirical news in Spanish presenting a system able to separate satirical from non-satirical news. More specifically, we concentrate on Twitter messages published by several satirical and non-satirical Twitter accounts. Our model represents each tweet with linguistically motivated features, which aim at capturing not the content but the style of the message. Our experiments demonstrate that our model outperforms a word-based baseline. We also show that or system detects satire independently from the Twitter account generating the messages.