SciELO - Scientific Electronic Library Online

 
 issue78THE CONSTRUCTION OF A COMPUTERIZED CORPUS OF WRITTEN ERRORS WITH TEXTS OF UNIVERSITY STUDENTS IN COLOMBIA author indexsubject indexarticles search
Home Pagealphabetic serial listing  

Services on Demand

Journal

Article

Indicators

Related links

  • On index processCited by Google
  • Have no similar articlesSimilars in SciELO
  • On index processSimilars in Google

Share


Lingüística y Literatura

Print version ISSN 0120-5587On-line version ISSN 2422-3174

Abstract

PEREZ PEREZ, Carlos Mario; QUIROZ HERRERA, Gabriel Ángel  and  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 Nov 09, 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.

Keywords : sentiment analysis; verb; direct object complement; poverty in Colombia; corpus linguistics.

        · abstract in Spanish     · text in Spanish     · Spanish ( pdf )