• português (Brasil)
    • English
    • español
  • English 
    • português (Brasil)
    • English
    • español
  • Login
About
  • Politics
  • Instructions to authors
  • Contact
    • Politics
    • Instructions to authors
    • Contact
View Item 
  •   Home
  • Centro de Educação e Ciências Humanas (CECH)
  • Programas de Pós-Graduação
  • Linguística (PPGL)
  • Teses e dissertações
  • View Item
  •   Home
  • Centro de Educação e Ciências Humanas (CECH)
  • Programas de Pós-Graduação
  • Linguística (PPGL)
  • Teses e dissertações
  • View Item
JavaScript is disabled for your browser. Some features of this site may not work without it.

Browse

All of DSpaceCommunities & CollectionsBy Issue DateAuthorsAdvisorTitlesSubjectsCNPq SubjectsGraduate ProgramDocument TypeThis CollectionBy Issue DateAuthorsAdvisorTitlesSubjectsCNPq SubjectsGraduate ProgramDocument Type

My Account

Login

ComentCorpus: identificação e pistas linguísticas para detecção de ironia no português do Brasil

Thumbnail
View/Open
Dissertação Final (1.904Mb)
Date
2018-03-16
Author
Pedro, Gabriela Wick
http://lattes.cnpq.br/3367416478527735
Metadata
Show full item record
Abstract
Opinions on the Web have been increasing progressively and, thus, has aroused interest in areas of study of Linguistics and Computation, for example. In this context comes the Sentiment Analysis, or Opinion Mining, which aims to analyze computationally opinions, emotions, feelings and subjectivities present in texts (LIU, 2012), however, certain subjective sentences can carry irony, transforming the meaning of a sentence. This dissertation aims to investigate expressions of irony in social media, focusing on the description of linguistic devices as clues of irony in opinion texts in Brazilian Portuguese. To understand the functioning of this figurative mechanism, we will start from the search a corpus constructed by new commentaries from the Folha de S. Paulo portal. In addiction, based on pragmatic and cognitive theories, we developed a corpus annotation scheme for opinions and their intentions: ironic, other types of irony or non-ironic. As a result, we have obtained a list of subcategories that characterize expressions of irony that allow to collaborate with the development of the NLP area and Sentiment Analysis and, in addition, to improve tools of automatic identification of opinion through the descriptions and the linguistic resources elaborated here.
URI
https://repositorio.ufscar.br/handle/ufscar/10710
Collections
  • Teses e dissertações

UFSCar
Universidade Federal de São Carlos - UFSCar
Send Feedback

UFSCar

IBICT
 

 


UFSCar
Universidade Federal de São Carlos - UFSCar
Send Feedback

UFSCar

IBICT