Eventually we proved that all the mentioned humor theories represented partial descriptions when related to satire, for we are forced to widen the spectrum of the explanatory account considering long satiric texts as real discursive practices. The final experimental step consisted in gradual attempts to automatically tag twenty new texts. Then a typological classification of the voices contained in the automatically collected lexicons it has been carried out using three linguistic traits – idiomatic, metaphorical and none – in order to assign to all the entries a feature, related to what kind of use the writers did of a specific item/sequence. The third chapter is dedicated to the description of the experimental part of the thesis: on a corpus composed of 112 political satire articles a human tagging activity has been carried out using a reduced (and modified with new criteria where needed) version of the Appraisal Framework (Martin & White, 2005). The purpose is to outline the best practises, trying to understand if (and how) it is possible to use them for more complex NLP tasks on long satiric text. The second chapter looks towards pros and cons of the computational approaches used for the resolution of different tasks related to the automatic processing of humorous texts. In the first chapter there is an attempt to define satire bringing into focus the specific features of the genre and analysing its connections with the already proposed humour theories. Īim of the thesis is a deeper understanding of satire in long texts. Our work in algorithmically identifying satirical news pieces can aid in minimizing the potential deceptive impact of satire. Our best predicting feature combination (Absurdity, Grammar and Punctuation) detects satirical news with a 90% precision and 84% recall (F-score=87%). Building on previous work in satire detection, we proposed an SVM-based algorithm, enriched with 5 predictive features (Absurdity, Humor, Grammar, Negative Affect, and Punctuation) and tested their combinations on 360 news articles. Satirical news stories were carefully matched and examined in contrast with their legitimate news counterparts in 12 contemporary news topics in 4 domains (civics, science, business, and “soft” news). This paper provides a conceptual overview of satire and humor, elaborating and illustrating the unique features of satirical news, which mimics the format and style of journalistic reporting. Whereas other types of fabrications aim to instill a false sense of truth in the reader, a successful satirical hoax must eventually be exposed as a jest. Satire is an attractive subject in deception detection research: it is a type of deception that intentionally incorporates cues revealing its own deceptiveness.
0 Comments
Leave a Reply.AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |