Lost in Translation: Viability of Machine Translation for Cross Language Sentiment Analysis
Recently there has been a lot of interest in Cross Language Sentiment Analysis (CLSA) using Machine Translation (MT) to facilitate Sentiment Analysis in resource deprived languages. The idea is to use the annotated resources of one language (say, L 1) for performing Sentiment Analysis in another language (say, L 2) which does not have annotated resources. The success of such a scheme crucially depends on the availability of a MT system between L 1 and L 2. We argue that such a strategy ignores the fact that a Machine Translation system is much more demanding in terms of resources than a Sentiment Analysis engine. Moreover, these approaches fail to take into account the divergence in the expression of sentiments across languages. We provide strong experimental evidence to prove that even the best of such systems do not outperform a system trained using only a few polarity annotated documents in the target language. Having a very large number of documents in L 1 also does not help because most Machine Learning approaches converge (or reach a plateau) after a certain training size (as demonstrated by our results). Based on our study, we take the stand that languages which have a genuine need for a Sentiment Analysis engine should focus on collecting a few polarity annotated documents in their language instead of relying on CLSA.
KeywordsMachine Translation Target Language Sentiment Analysis Source Language Movie Review
Unable to display preview. Download preview PDF.
- 1.Brown, P.F., Pietra, V.J.D., Pietra, S.A.D., Mercer, R.L.: The mathematics of statistical machine translation: parameter estimation. Comput. Linguist. 19, 263–311 (1993)Google Scholar
- 2.Pang, B., Lee, L.: Thumbs up? sentiment classification using machine learning techniques. In: Proceedings of EMNLP 2002, pp. 79–86 (2002)Google Scholar
- 3.Mihalcea, R., Banea, C., Wiebe, J.: Learning multilingual subjective language via cross-lingual projections. In: ACL (2007)Google Scholar
- 4.Banea, C., Mihalcea, R., Wiebe, J., Hassan, S.: Multilingual subjectivity analysis using machine translation. In: EMNLP, pp. 127–135 (2008)Google Scholar
- 5.Wan, X.: Co-training for cross-lingual sentiment classification. In: ACL/AFNLP, pp. 235–243 (2009)Google Scholar
- 6.Wei, B., Pal, C.: Cross lingual adaptation: an experiment on sentiment classifications. In: Proceedings of the ACL 2010 Conference Short Papers, ACLShort 2010, pp. 258–262. Association for Computational Linguistics, Stroudsburg (2010)Google Scholar
- 7.Brooke, J., Tofiloski, M., Taboada, M.: Cross-linguistic sentiment analysis: From english to spanish. In: International Conference on Recent Advances in NLP (2009)Google Scholar
- 8.Zagibalov, T.: Unsupervised and knowledge-poor approaches to sentiment analysis. PhD thesis, University of Sussex (2010)Google Scholar