Sentiment polarity classification of tweets using an extended dictionary

Vladimir Vargas-Calderón, Nelson A.Vargas Sánchez, Liliana Calderón-Benavides, Jorge E. Camargo

Research output: Articles / NotesScientific Articlepeer-review

4 Scopus citations


With the purpose of classifying text based on its sentiment polarity (positive or negative), we proposed an extension of a 68,000 tweets corpus through the inclusion of word definitions from a dictionary of the Real Academia Española de la Lengua (RAE). A set of 28,000 combinations of 6 Word2Vec and support vector machine parameters were considered in order to evaluate how positively would affect the inclusion of a RAE’s dictionary definitions classification performance. We found that such a corpus extension significantly improve the classification accuracy. Therefore, we conclude that the inclusion of a RAE’s dictionary increases the semantic relations learned by Word2Vec allowing a better classification accuracy.

Original languageEnglish
Pages (from-to)1-11
Number of pages11
JournalInteligencia Artificial
Issue number62
StatePublished - 7 Sep 2018


  • Corpus extension
  • Polarity
  • Semantics
  • Sentiment analysis
  • Support vector machine
  • Word2vec


Dive into the research topics of 'Sentiment polarity classification of tweets using an extended dictionary'. Together they form a unique fingerprint.

Cite this