Dissertação de Mestrado
A comparative study of machine translation for multilingual sentence-level sentiment analysis
Fecha
2017-06-26Autor
Matheus Lima Diniz Araujo
Institución
Resumen
Sentiment analysis has become a key tool for several social media applications. Despite the significant interest in this theme and amount of research efforts in the field, almost all existing methods are designed to work with only English content. So, we provide an extensive quantitative analysis of existing multi-language approaches against state-of-the-art English methods with the help of machine translation tools in fourteen different human labeled datasets in various idioms. Our results suggest that simply translating the input text on a specific language to English and then using one of the existing best methods developed to English can be better than the existing language specific efforts evaluated. As a final contribution to the research community, we release the iFeel 3.0 system, a web framework for multilingual sentence-level sentiment analysis. We hope our system setups a new baseline for future sentence-level methods developed in a wide set of languages.