Premium
A knowledge‐based approach for polarity classification in T witter
Author(s) -
MontejoRáez Arturo,
MartínezCámara Eugenio,
MartínValdivia M. Teresa,
UreñaLópez L. Alfonso
Publication year - 2014
Publication title -
journal of the association for information science and technology
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 0.903
H-Index - 145
eISSN - 2330-1643
pISSN - 2330-1635
DOI - 10.1002/asi.22984
Subject(s) - polarity (international relations) , weighting , artificial intelligence , computer science , mathematics , pattern recognition (psychology) , natural language processing , physics , chemistry , acoustics , cell , biochemistry
Until now, most of the methods published for polarity classification in T witter have used a supervised approach. The differences between them are only the features selected and the method used for weighting them. In this article, we present an unsupervised method for polarity classification in T witter. The method is based on the expansion of the concepts expressed in the tweets through the application of P age R ank to W ord N et. In addition, we integrate S enti W ord N et to compute the final value of polarity. The synsets values are weighted with the P age R ank scores obtained in the previous random walk process over W ord N et. The results obtained show that disambiguation and expansion are good strategies for improving overall performance.