Lexicon-Based Sentiment Analysis for Reviews of Products in Brazilian Portuguese

Author

Avanco, Lucas V. ; Nunes, Maria G. V.

Author_Institution

Interinstitutional Center for Comput. Linguistics (NILC) Inst. of Math. & Comput. Sci., Univ. of Sao Paulo, Sao Paulo, Brazil

fYear

2014

fDate

18-22 Oct. 2014

Firstpage

277

Lastpage

281

Abstract

This paper presents some results on lexicon-based classification of sentiment polarity in web reviews of products written in Brazilian Portuguese. They represent a first step towards a robust opinion miner from reviews of technology products. The evaluation shows the performance of 3 different sentiment lexicons combined with simple strategies. It is also discussed the risk of considering the rating provided by the writers for the purpose of evaluating the algorithms. The results show that the better combination is the version of the algorithm that deals also with negation and intensification and uses the sentiment lexicon Sent ilex. The average F-measure achieved 0.73.

Keywords

Internet; data mining; natural language processing; pattern classification; Brazilian Portuguese; lexicon-based classification; lexicon-based sentiment analysis; natural language processing; opinion miner; product Web review; sentiment lexicon Sent ilex; sentiment polarity; technology product review; Accuracy; Context; Pragmatics; Semantics; Sentiment analysis; Opinion Mining; Polarity Classification; Sentiment Analysis; Sentiment Lexicon;

fLanguage

English

Publisher

ieee

Conference_Titel

Intelligent Systems (BRACIS), 2014 Brazilian Conference on

Conference_Location

Sao Paulo

Type

conf

DOI

10.1109/BRACIS.2014.57

Filename

6984843