NILC_USP: an improved hybrid system for sentiment analysis in Twitter messages.

dc.creatorBalage Filho, Pedro Paulo
dc.creatorAvanço, Lucas Vinicius
dc.creatorPardo, Thiago Alexandre Salgueiro
dc.creatorNunes, Maria das Graças Volpe
dc.date.accessioned2014-09-24T21:32:18Z
dc.date.accessioned2018-07-04T16:51:50Z
dc.date.available2014-09-24T21:32:18Z
dc.date.available2018-07-04T16:51:50Z
dc.date.created2014-09-24T21:32:18Z
dc.date.issued2014-08
dc.identifierInternational Workshop on Semantic Evaluation, 8th, 2014, Dublin.
dc.identifier9781941643242
dc.identifierhttp://www.producao.usp.br/handle/BDPI/46188
dc.identifierhttp://alt.qcri.org/semeval2014/cdrom/pdf/SemEval074.pdf
dc.identifier.urihttp://repositorioslatinoamericanos.uchile.cl/handle/2250/1641402
dc.description.abstractThis paper describes the NILC USP system that participated in SemEval-2014 Task 9: Sentiment Analysis in Twitter, a re-run of the SemEval 2013 task under the same name. Our system is an improved version of the system that participated in the 2013 task. This system adopts a hybrid classification process that uses three classification approaches: rule-based, lexiconbased and machine learning. We suggest a pipeline architecture that extracts the best characteristics from each classifier. In this work, we want to verify how this hybrid approach would improve with better classifiers. The improved system achieved an F-score of 65.39% in the Twitter message-level subtask for 2013 dataset (+ 9.08% of improvement) and 63.94% for 2014 dataset.
dc.languageeng
dc.publisherACL Special Interest Group on the Lexicon - SIGLEX
dc.publisherDublin City University - DCU
dc.publisherDublin
dc.relationInternational Workshop on Semantic Evaluation, 8th
dc.rightshttp://creativecommons.org/licenses/by/3.0/br/
dc.rightsCopyright The authors
dc.rightsopenAccess
dc.titleNILC_USP: an improved hybrid system for sentiment analysis in Twitter messages.
dc.typeActas de congresos


Este ítem pertenece a la siguiente institución