Cover Image

Combination of multi-view multi-source language classifiers for cross-lingual sentiment classification

Cross-lingual sentiment classification aims to conduct sentiment classification in a target language using labeled sentiment data in a source language. Most existing research works rely on machine translation to directly project information from one language to another. But cross-lingual classifiers...

Full description

Saved in:
Bibliographic Details
Main Authors: Hajmohammadi, Mohammad Sadegh, Ibrahim, Roliana, Selamat, Ali, Yousefpour, Alireza
Format: Article
Published: Springer Verlag 2014
Subjects:
QA75 Electronic computers. Computer science
Online Access:http://eprints.utm.my/id/eprint/52143/
http://dx.doi.org/10.1007/978-3-319-05476-6_3
Tags: Add Tag
No Tags, Be the first to tag this record!
id my.utm.52143
record_format eprints
spelling my.utm.521432019-01-28T04:44:56Z http://eprints.utm.my/id/eprint/52143/ Combination of multi-view multi-source language classifiers for cross-lingual sentiment classification Hajmohammadi, Mohammad Sadegh Ibrahim, Roliana Selamat, Ali Yousefpour, Alireza QA75 Electronic computers. Computer science Cross-lingual sentiment classification aims to conduct sentiment classification in a target language using labeled sentiment data in a source language. Most existing research works rely on machine translation to directly project information from one language to another. But cross-lingual classifiers always cannot learn all characteristics of target language data by using only translated data from one language. In this paper, we propose a new learning model that uses labeled sentiment data from more than one language to compensate some of the limitations of resource translation. In this model, we first create different views of sentiment data via machine translation, then train individual classifiers in every view and finally combine the classifiers for final decision. We have applied this model to the sentiment classification datasets in three different languages using different combination methods. The results show that the combination methods improve the performances obtained separately by each individual classifier. Springer Verlag 2014 Article PeerReviewed Hajmohammadi, Mohammad Sadegh and Ibrahim, Roliana and Selamat, Ali and Yousefpour, Alireza (2014) Combination of multi-view multi-source language classifiers for cross-lingual sentiment classification. Intelligent Information and Database Systems, Pt 1, 8397 L (Part 1). pp. 21-30. ISSN 1611-3349 http://dx.doi.org/10.1007/978-3-319-05476-6_3 DOI: 10.1007/978-3-319-05476-6_3
institution Universiti Teknologi Malaysia
building UTM Library
collection Institutional Repository
continent Asia
country Malaysia
content_provider Universiti Teknologi Malaysia
content_source UTM Institutional Repository
url_provider http://eprints.utm.my/
topic QA75 Electronic computers. Computer science
spellingShingle QA75 Electronic computers. Computer science
Hajmohammadi, Mohammad Sadegh
Ibrahim, Roliana
Selamat, Ali
Yousefpour, Alireza
Combination of multi-view multi-source language classifiers for cross-lingual sentiment classification
description Cross-lingual sentiment classification aims to conduct sentiment classification in a target language using labeled sentiment data in a source language. Most existing research works rely on machine translation to directly project information from one language to another. But cross-lingual classifiers always cannot learn all characteristics of target language data by using only translated data from one language. In this paper, we propose a new learning model that uses labeled sentiment data from more than one language to compensate some of the limitations of resource translation. In this model, we first create different views of sentiment data via machine translation, then train individual classifiers in every view and finally combine the classifiers for final decision. We have applied this model to the sentiment classification datasets in three different languages using different combination methods. The results show that the combination methods improve the performances obtained separately by each individual classifier.
format Article
author Hajmohammadi, Mohammad Sadegh
Ibrahim, Roliana
Selamat, Ali
Yousefpour, Alireza
author_facet Hajmohammadi, Mohammad Sadegh
Ibrahim, Roliana
Selamat, Ali
Yousefpour, Alireza
author_sort Hajmohammadi, Mohammad Sadegh
title Combination of multi-view multi-source language classifiers for cross-lingual sentiment classification
title_short Combination of multi-view multi-source language classifiers for cross-lingual sentiment classification
title_full Combination of multi-view multi-source language classifiers for cross-lingual sentiment classification
title_fullStr Combination of multi-view multi-source language classifiers for cross-lingual sentiment classification
title_full_unstemmed Combination of multi-view multi-source language classifiers for cross-lingual sentiment classification
title_sort combination of multi-view multi-source language classifiers for cross-lingual sentiment classification
publisher Springer Verlag
publishDate 2014
url http://eprints.utm.my/id/eprint/52143/
http://dx.doi.org/10.1007/978-3-319-05476-6_3
_version_ 1643653163348131840
score 13.211869

Similar Items