Cross-lingual polarity detection with machine translation

E. Demirtaş, M. Pechenizkiy

Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

23 Citations (Scopus)
1 Downloads (Pure)

Abstract

Recent advancements in machine translation foster an interest of its use in sentiment analysis. In this paper, we investigate prospects and limitations of machine translation in sentiment analysis for cross-lingual polarity detection task. We focus on improving classification accuracy in a cross-lingual setting where we have available labeled training instances about particular domain in different languages. We experiment with movie review and product review datasets consisting of polar texts in English and Turkish. The results of the study show that expanding training size with new instances taken from another corpus does not necessarily increase classification accuracy. And this happens primarily not due to (not always accurate) machine translation, but because of the inherent differences in corpora between two subsets written in different languages. Similarly, in case of co-training classification with machine translation we observe from the results that accuracy improvement can be explained by semi-supervised learning with unlabeled data coming from the same domain, but not due to cross-language co-training itself. Our results also show that amount of artificial noise added by machine translation services does not hinder classifiers much in polarity detection task. However, it is important to distinguish the effect of machine translation from the effect of merging different cross-lingual data sources and that like in case of transfer learning we may need to search for ways to account for cross-lingual data distribution differences.
Original languageEnglish
Title of host publicationProceedings of the Second International Workshop on Issues of Sentiment Discovery and Opinion Mining (WISDOM'13, Chicago IL, USA, August 11, 2013; in conjunction with SIGKDD'13)
Place of PublicationNew York NY
PublisherAssociation for Computing Machinery, Inc
Pages9/1-8
ISBN (Print)978-1-4503-2332-1
DOIs
Publication statusPublished - 2013
Eventconference; Second International Workshop on Issues of Sentiment Discovery and Opinion Mining; 2013-08-11; 2013-08-11 -
Duration: 11 Aug 201311 Aug 2013

Conference

Conferenceconference; Second International Workshop on Issues of Sentiment Discovery and Opinion Mining; 2013-08-11; 2013-08-11
Period11/08/1311/08/13
OtherSecond International Workshop on Issues of Sentiment Discovery and Opinion Mining

Fingerprint Dive into the research topics of 'Cross-lingual polarity detection with machine translation'. Together they form a unique fingerprint.

  • Cite this

    Demirtaş, E., & Pechenizkiy, M. (2013). Cross-lingual polarity detection with machine translation. In Proceedings of the Second International Workshop on Issues of Sentiment Discovery and Opinion Mining (WISDOM'13, Chicago IL, USA, August 11, 2013; in conjunction with SIGKDD'13) (pp. 9/1-8). Association for Computing Machinery, Inc. https://doi.org/10.1145/2502069.2502078