Sentiment Analysis of Code-Mixed Bambara-French Social Media Text Using Deep Learning Techniques
- 17 May 2018
- journal article
- computer science
- Published by EDP Sciences in Wuhan University Journal of Natural Sciences
- Vol. 23 (3), 237-243
- https://doi.org/10.1007/s11859-018-1316-z
Abstract
The global growth of the Internet and the rapid expansion of social networks such as Facebook make multilingual sentiment analysis of social media content very necessary. This paper performs the first sentiment analysis on code-mixed Bambara-French Facebook comments. We develop four Long Short-term Memory (LSTM)-based models and two Convolutional Neural Network (CNN)-based models, and use these six models, Naïve Bayes, and Support Vector Machines (SVM) to conduct experiments on a constituted dataset. Social media text written in Bambara is scarce. To mitigate this weakness, this paper uses dictionaries of character and word indexes to produce character and word embedding in place of pre-trained word vectors. We investigate the effect of comment length on the models and perform a comparison among them. The best performing model is a one-layer CNN deep learning model with an accuracy of 83.23 %.Keywords
This publication has 12 references indexed in Scilit:
- Twitter as a Corpus for Sentiment Analysis and Opinion MiningIJARCCE, 2016
- Chinese Sentiment Analysis Using Bidirectional LSTM with Word EmbeddingPublished by Springer Science and Business Media LLC ,2016
- Multilingual Code-switching Identification via LSTM Recurrent Neural NetworksPublished by Association for Computational Linguistics (ACL) ,2016
- Twitter Sentiment Analysis Using Deep Convolutional Neural NetworkPublished by Springer Science and Business Media LLC ,2015
- RETRACTED: Evaluation of modulation transfer function of optical lens system by support vector regression methodologies – A comparative studyInfrared Physics & Technology, 2014
- Bamana Reference Corpus (BRC)Procedia - Social and Behavioral Sciences, 2013
- Interactional otherness: Towards a redefinition of codeswitchingInternational Journal of Bilingualism, 2002
- Gradient-based learning applied to document recognitionProceedings of the IEEE, 1998
- Long Short-Term MemoryNeural Computation, 1997
- Code-switching and grammatical theoryPublished by Cambridge University Press (CUP) ,1995