This paper presents computational work to detect satire/sarcasm in long commentaries on Italian politics. It uses the lexica extracted from the manual annotation of some 30K word texts based on Appraisal Theory. The underlying hypothesis is that using this framework it is possible to pinpoint precisely ironic content through the deep semantic analysis of evaluative judgement and appreciation. The paper presents the manual annotation phase realized on 112 texts by two well-known Italian journalists. After a first experimentation based on the lexicons extracted from the xml output files, we proceed to retag lexical entries dividing them up into two subclasses: with figurative or literal meaning. Eventually more fine-grained Appraisal features are derived and more experiments are carried out and compared to results obtained by a lean sentiment analysis. The final output is produced from held out texts to verify the usefulness of the lexica and the Appraisal theory in detecting ironic content.
|Titolo:||Detecting Satire in Italian Political Commentaries|
|Autori interni:||DELMONTE, Rodolfo|
|Data di pubblicazione:||2016|
|Appare nelle tipologie:||3.1 Articolo su libro|