Home // DATA ANALYTICS 2016, The Fifth International Conference on Data Analytics // View article

The Impact of Machine Translation on Sentiment Analysis

Authors:
Gayane Shalunts
Gerhard Backfried
Nicolas Commeignes

Keywords: Sentiment analysis; machine translation.

Abstract:
The article explores the impact of Machine Translation on sentiment analysis, employing the combination of two state-of-the-art tools - the multilingual sentiment analysis tool SentiSAIL and the Machine Translation tool SDL Language Weaver. The original corpora are in German, Russian and Spanish in the domain of general news. The output language of translation is English. Firstly, the work presents the development and evaluation of SentiSAIL features in a newly supported language - Spanish. Further experimental setup reveals that the performance rates of sentiment analysis on the original and translated corpora are comparable. Thus a given tool, performing high quality Machine Translation from a target language to English, can eliminate the necessity to develop specific sentiment analysis resources for that language.

Pages: 51 to 56

Copyright: Copyright (c) IARIA, 2016

Publication date: October 9, 2016

Published in: conference

ISSN: 2308-4464

ISBN: 978-1-61208-510-4

Location: Venice, Italy

Dates: from October 9, 2016 to October 13, 2016