Abstract | ||
---|---|---|
The past years have shown a steady growth in interest in the Natural Language Processing task of sentiment analysis. The research community in this field has actively proposed and improved methods to detect and classify the opinions and sentiments expressed in different types of text - from traditional press articles, to blogs, reviews, fora or tweets. A less explored aspect has remained, however, the issue of dealing with sentiment expressed in texts in languages other than English. To this aim, the present article deals with the problem of sentiment detection in three different languages - French, German and Spanish - using three distinct Machine Translation (MT) systems - Bing, Google and Moses. Our extensive evaluation scenarios show that SMT systems are mature enough to be reliably employed to obtain training data for languages other than English and that sentiment analysis systems can obtain comparable performances to the one obtained for English. |
Year | Venue | Keywords |
---|---|---|
2012 | WASSA@ACL | sentiment analysis system,multilingual sentiment analysis,explored aspect,comparable performance,smt system,machine translation,natural language processing task,different type,different language,sentiment detection,distinct machine translation,sentiment analysis |
Field | DocType | Volume |
Training set,Computer science,Sentiment analysis,Machine translation,Natural language processing,Artificial intelligence,German | Conference | W12-37 |
Citations | PageRank | References |
29 | 1.24 | 19 |
Authors | ||
2 |
Name | Order | Citations | PageRank |
---|---|---|---|
Alexandra Balahur | 1 | 593 | 40.19 |
Marco Turchi | 2 | 560 | 57.79 |