Comparing Approaches to Subjectivity Classification: A Study on Portuguese Tweets

Siliva Moraes, Andre Santos*, Matheus Redecker, Rackel Machado, Felipe Meneguzzi

*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceedingPublished conference contribution

6 Citations (Scopus)

Abstract

In this paper, we compare lexicon-based and machine learning-based approaches to define the subjectivity of tweets in Portuguese. We tested SentiLex and WordAffectBR lexicons, and Sequential Machine Optimization and Naive Bayes algorithms for this task. In our study, we used the Computer-BR corpus that contains messages about the technology area. We obtained better results using the Comprehensive Measurement Feature Selection method and the Sequential Machine Optimization algorithm as the classifier. We achieved considerable accuracy when we included the polarities of words in the vector space model of tweets.
Original languageEnglish
Title of host publicationComputational Processing of the Portuguese Language
Subtitle of host publicationPROPOR 2016
EditorsJ. Silva, R Ribeiro, P. Quaresma, A. Adami, A. Branco
PublisherSpringer
Pages86-94
Number of pages9
ISBN (Electronic)978-3-319-41552-9
ISBN (Print)978-3-319-41551-2
DOIs
Publication statusPublished - 21 Jun 2016

Publication series

NameLecture Notes in Computer Science
Volume9727

Fingerprint

Dive into the research topics of 'Comparing Approaches to Subjectivity Classification: A Study on Portuguese Tweets'. Together they form a unique fingerprint.

Cite this