SciELO - Scientific Electronic Library Online

 
 número78THE CONSTRUCTION OF A COMPUTERIZED CORPUS OF WRITTEN ERRORS WITH TEXTS OF UNIVERSITY STUDENTS IN COLOMBIA índice de autoresíndice de assuntospesquisa de artigos
Home Pagelista alfabética de periódicos  

Serviços Personalizados

Journal

Artigo

Indicadores

Links relacionados

  • Em processo de indexaçãoCitado por Google
  • Não possue artigos similaresSimilares em SciELO
  • Em processo de indexaçãoSimilares em Google

Compartilhar


Lingüística y Literatura

versão impressa ISSN 0120-5587versão On-line ISSN 2422-3174

Resumo

PEREZ PEREZ, Carlos Mario; QUIROZ HERRERA, Gabriel Ángel  e  TAMAYO HERRERA, Antonio Jesús. DOES PREDICATIVE STRUCTURE [VERB + DIRECT OBJECT] HAVE PREDICTIVE CHARACTER? A SYNTACTIC-SEMANTIC CHARACTERIZATION FOR SENTIMENT ANALYSIS PURPOSES. Linguist.lit. [online]. 2020, n.78, pp.11-34.  Epub 09-Nov-2021. ISSN 0120-5587.  https://doi.org/10.17533/udea.lyl.n78a01.

Traditionally, sentiment analysis has focused on processing less complex textual units, as sentences, through detailed characterization of their components like adjectives. However, there are other types of units, such as predicative structures, that might be discriminant elements of more complex discursive units like the news. Thus, in this article, word occurrences of the predicative structure [verb + direct object] are extracted and characterized from a corpus on poverty compiled from Colombian newspapers. The results demonstrate that these units are discriminant and might help with polarity classification.

Palavras-chave : sentiment analysis; verb; direct object complement; poverty in Colombia; corpus linguistics.

        · resumo em Espanhol     · texto em Espanhol     · Espanhol ( pdf )