A Word-Character Convolutional Neural Network for Language-Agnostic Twitter Sentiment Analysis

Zhang, S, Zhang, J and Chan, J 2017, 'A Word-Character Convolutional Neural Network for Language-Agnostic Twitter Sentiment Analysis', in Bevan Koopman, Guido Zuccon and Mark Carman (ed.) Proceedings of the 22nd Australasian Document Computing Symposium (ADCS 2017), Brisbane, Australia, 7-8 December 2017, pp. 12-18.


Document type: Conference Paper
Collection: Conference Papers

Title A Word-Character Convolutional Neural Network for Language-Agnostic Twitter Sentiment Analysis
Author(s) Zhang, S
Zhang, J
Chan, J
Year 2017
Conference name ADCS 2017
Conference location Brisbane, Australia
Conference dates 7-8 December 2017
Proceedings title Proceedings of the 22nd Australasian Document Computing Symposium (ADCS 2017)
Editor(s) Bevan Koopman, Guido Zuccon and Mark Carman
Publisher Association for Computing Machinery
Place of publication New York, United States
Start page 12
End page 18
Total pages 7
Abstract Convolutional Neural Networks (CNN) have been widely used for text classification. Both word-based CNNs and character-based CNNs have shown good performance for Twitter sentiment classification. Most research on CNNs is towards English Twitter sentiment analysis and language-independent sentiment classification is still a challenging task due to the lack of non-English resources. Recently there are several works using character-based CNNs for tackling the language-independence challenge. Motivated by the intuition that the word-level and character-level deep features contain complimentary information, we propose a hybrid word-character CNN for language-agnostic Twitter sentiment classification. Word-character CNN comprises two convolutional channels, one for word-level convolution and one for character-level convolution, and a merge layer is included in our model for combining features from two convolutional channels. Moreover, our model does not require language identification and do not use unsupervised embeddings or other external resources. Our proposed model can achieve more superior performance on language-agnostic Twitter sentiment classification than word-based CNNs and character-based CNNs.
Subjects Pattern Recognition and Data Mining
Keyword(s) Twitter
language independent
convolutional neural network
sentiment analysis
text classication
DOI - identifier 10.1145/3166072.3166082
Copyright notice © 2017 Copyright held by the owner/author(s). Publication rights licensed to ACM.
ISBN 9781450363914
Versions
Version Filter Type
Citation counts: Scopus Citation Count Cited 0 times in Scopus Article
Altmetric details:
Access Statistics: 13 Abstract Views  -  Detailed Statistics
Created: Thu, 06 Dec 2018, 10:39:00 EST by Catalyst Administrator
© 2014 RMIT Research Repository • Powered by Fez SoftwareContact us