DEEP LEARNING MODEL FOR BILINGUAL SENTIMENT CLASSIFICATION OF SHORT TEXTS
Sentiment analysis of short texts such as Twitter messages and comments in news portals is challenging due to the lack of contextual information. We propose a deep neural network model that uses bilingual word embeddings to effectively solve sentiment classification problem for a given pair of langu...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Saint Petersburg National Research University of Information Technologies, Mechanics and Optics (ITMO University)
2017-01-01
|
| Series: | Naučno-tehničeskij Vestnik Informacionnyh Tehnologij, Mehaniki i Optiki |
| Subjects: | |
| Online Access: | http://ntv.ifmo.ru/file/article/16415.pdf |
| _version_ | 1818966658543255552 |
|---|---|
| author | Y. B. Abdullin V. V. Ivanov |
| author_facet | Y. B. Abdullin V. V. Ivanov |
| author_sort | Y. B. Abdullin |
| collection | DOAJ |
| description | Sentiment analysis of short texts such as Twitter messages and comments in news portals is challenging due to the lack of contextual information. We propose a deep neural network model that uses bilingual word embeddings to effectively solve sentiment classification problem for a given pair of languages. We apply our approach to two corpora of two different language pairs: English-Russian and Russian-Kazakh. We show how to train a classifier in one language and predict in another. Our approach achieves 73% accuracy for English and 74% accuracy for Russian. For Kazakh sentiment analysis, we propose a baseline method, that achieves 60% accuracy; and a method to learn bilingual embeddings from a large unlabeled corpus using a bilingual word pairs. |
| first_indexed | 2024-12-20T13:36:24Z |
| format | Article |
| id | doaj.art-58bcf62739dd46a895ab9ce7dc1ba5a4 |
| institution | Directory Open Access Journal |
| issn | 2226-1494 2500-0373 |
| language | English |
| last_indexed | 2024-12-20T13:36:24Z |
| publishDate | 2017-01-01 |
| publisher | Saint Petersburg National Research University of Information Technologies, Mechanics and Optics (ITMO University) |
| record_format | Article |
| series | Naučno-tehničeskij Vestnik Informacionnyh Tehnologij, Mehaniki i Optiki |
| spelling | doaj.art-58bcf62739dd46a895ab9ce7dc1ba5a42022-12-21T19:38:56ZengSaint Petersburg National Research University of Information Technologies, Mechanics and Optics (ITMO University)Naučno-tehničeskij Vestnik Informacionnyh Tehnologij, Mehaniki i Optiki2226-14942500-03732017-01-0117112913610.17586/2226-1494-2017-17-1-129-136DEEP LEARNING MODEL FOR BILINGUAL SENTIMENT CLASSIFICATION OF SHORT TEXTSY. B. Abdullin0V. V. Ivanov1software developer, «Hibrain» LTD, Astana, 010000, Kazakhstan; junior scientific researcher, Kazan Federal University, Kazan, 420008, Russian FederationPhD, scientific researcher, Innopolis University, Innopolis, 420500, Russian FederationSentiment analysis of short texts such as Twitter messages and comments in news portals is challenging due to the lack of contextual information. We propose a deep neural network model that uses bilingual word embeddings to effectively solve sentiment classification problem for a given pair of languages. We apply our approach to two corpora of two different language pairs: English-Russian and Russian-Kazakh. We show how to train a classifier in one language and predict in another. Our approach achieves 73% accuracy for English and 74% accuracy for Russian. For Kazakh sentiment analysis, we propose a baseline method, that achieves 60% accuracy; and a method to learn bilingual embeddings from a large unlabeled corpus using a bilingual word pairs.http://ntv.ifmo.ru/file/article/16415.pdfsentiment analysisbilingual word embeddingsrecurrent neural networksdeep learningKazakh language |
| spellingShingle | Y. B. Abdullin V. V. Ivanov DEEP LEARNING MODEL FOR BILINGUAL SENTIMENT CLASSIFICATION OF SHORT TEXTS Naučno-tehničeskij Vestnik Informacionnyh Tehnologij, Mehaniki i Optiki sentiment analysis bilingual word embeddings recurrent neural networks deep learning Kazakh language |
| title | DEEP LEARNING MODEL FOR BILINGUAL SENTIMENT CLASSIFICATION OF SHORT TEXTS |
| title_full | DEEP LEARNING MODEL FOR BILINGUAL SENTIMENT CLASSIFICATION OF SHORT TEXTS |
| title_fullStr | DEEP LEARNING MODEL FOR BILINGUAL SENTIMENT CLASSIFICATION OF SHORT TEXTS |
| title_full_unstemmed | DEEP LEARNING MODEL FOR BILINGUAL SENTIMENT CLASSIFICATION OF SHORT TEXTS |
| title_short | DEEP LEARNING MODEL FOR BILINGUAL SENTIMENT CLASSIFICATION OF SHORT TEXTS |
| title_sort | deep learning model for bilingual sentiment classification of short texts |
| topic | sentiment analysis bilingual word embeddings recurrent neural networks deep learning Kazakh language |
| url | http://ntv.ifmo.ru/file/article/16415.pdf |
| work_keys_str_mv | AT ybabdullin deeplearningmodelforbilingualsentimentclassificationofshorttexts AT vvivanov deeplearningmodelforbilingualsentimentclassificationofshorttexts |