Linguistic analysis model for monitoring user reaction on satirical news for Brazilian Portuguese

The presence of misleading content on the web and messaging applications has proven to be a major contemporary problem. This context has generated some initiatives in Linguistics and Computation to investigate not only the informative content but also the media in which this mis/disinformation circulates. This paper describes one initiative, in particular, with satire. We present a linguistic analysis based on Brazilian Portuguese satirical news, seeking to understand how a user receives and shares this type of information and which are the main linguistic characteristics of these comments. We note that, while many users understand satirical content, many use the virtual/social environment to express a general comment about the news subject or even to make a toxic comment about a public person. Through this work, we intend to collaborate with the detection of misleading content and understand the behaviour of the user of social media, avoiding the improper sharing of this kind of news.