Publication at Faculty of Mathematics and Physics |
2013
Abstract
Lexicon-based classifier is in the long term one of the main and most effective methods of polarity classification used in sentiment analy-sis, i.e. computational study of opinions, sen-timents and emotions expressed in text (see Liu, 2010). Although it achieves relatively good results also for Czech, the classifier still shows some error rate.
This paper provides a detailed analysis of such errors caused both by the system and by human reviewers. The identified errors are representatives of the chal-lenges faced by the entire area of opinion min-ing.
Therefore, the analysis is essential for fur-ther research in the field and serves as a basis for meaningful improvements of the system.