Experiments using varying sizes and machine translated data for sentiment analysis in Twitter

In this paper we present several experiments for the task entitled sentiment analysis at global level within the TASS evaluation campaign. The aim of this task is to assess the global polarity of Spanish short texts extracted from Twitter. To tackle this task, an approach based on machine learning by trying different feature combinations was applied. Several in-house built dictionaries and machinetranslated data for training were employed by adapting an approach designed for English to Spanish. Additionally, four separate classifiers were tested in cascade to determine the sentiment from the general to the finer-grained classes of polarity. Although this is our first participation, the proposed approaches might be considered good strategies to generate learning data for polarity classification systems in Spanish.

BALAHUR DOBRESCU Alexandra;  PEREA ORTEGA Jose Manuel; 

2013-10-14

SOCIEDAD ESPANOLA PARA EL PROCESAMIENTO DEL LENGUAJE NATURAL

JRC84255

978-84-695-8349-4,   

http://www.congresocedi.es/images/site/actas/ActasSEPLN.pdf,    https://publications.jrc.ec.europa.eu/repository/handle/JRC84255,