Abstract
Tunisians on social media tend to express themselves in their local dialect using Latin script (TUNIZI). This raises an additional challenge to the process of exploring and recognizing online opinions. To date, very little work has addressed TUNIZI sentiment analysis due to scarce resources for training an automated system. In this paper, we focus on the Tunisian dialect sentiment analysis used on social media. Most of the previous work used machine learning techniques combined with handcrafted features. More recently, Deep Neural Networks were widely used for this task, especially for the English language. In this paper, we explore the importance of various unsupervised word representations (word2vec, BERT) and we investigate the use of Convolutional Neural Networks and Bidirectional Long Short-Term Memory. Without using any kind of handcrafted features, our experimental results on two publicly available datasets [18, 19] showed comparable performances to other languages.
Supported by iCompass.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
Wicked.
- 2.
Expensive.
References
Mulki, H., Haddad, H., Babaoglu, I.: Modern trends in Arabic sentiment analysis: a survey. Traitement Automatique des Langues 58(3), 15–39 (2018)
Guellil, I. and Azouaou, F. and Valitutti, A.: English vs Arabic sentiment analysis: a survey presenting 100 work studies, resources and tools. In: 16th International Conference on Computer Systems and Applications, pp. 1–8. IEEE Computer Society Conference Publishing Services, Abu Dhabi (2019)
Medhaffar, S., Bougares, F., Estève, Y. and Hadrich-Belguith, L.: Sentiment analysis of Tunisian dialects: linguistic resources and experiments. In: 3rd Arabic Natural Language Processing Workshop, pp. 55–61. Association for Computational Linguistics, Valencia (2017)
Masmoudi, A., Khmekhem, M., Khrouf, M., Hadrich-Belguith, L.: Transliteration of Arabizi into Arabic script for Tunisian dialect. ACM Trans. Asian Low-Resour. Lang. Inf. Process. 19(2), 1–21 (2019)
Qwaider, C., Chatzikyriakidis, S., Dobnik, S.: Can modern standard Arabic approaches be used for Arabic dialects? Sentiment analysis as a case study. In: 3rd Workshop on Arabic Corpus Linguistics, pp. 40–50. Association for Computational Linguistics, Cardiff (2019)
Stevens, P.B.: Ambivalence, modernisation and language attitudes: French and Arabic in Tunisia. J. Multiling. Multicult. Dev. 4(2–3), 101–114 (1983)
Skandrani, H., Triki, A.: Trust in supply chains, meanings, determinants and demonstrations: a qualitative study in an emerging market context. Qual. Mark. Res. 14(4), 391–409 (2011)
Fourati, C. and Messaoudi, A. and Haddad, H.: TUNIZI: a Tunisian Arabizi sentiment analysis Dataset. arXiv preprint arXiv:2004.14303
Younes, J., Achour, H., Souissi, E.: Constructing linguistic resources for the Tunisian dialect using textual user-generated contents on the social web. ICWE 2015. LNCS, vol. 9396, pp. 3–14. Springer, Cham (2015). https://doi.org/10.1007/978-3-319-24800-4_1
Abidi, K.: Automatic Building of Multilingual Resources from Social Networks: Application to Maghrebi Dialects (Doctoral Dissertation). Université de Lorraine, France (2019)
Younes, J., Achour, H., Souissi, E., Ferchichi, A.: Survey on corpora availability for the Tunisian dialect automatic processing. In: JCCO Joint International Conference on ICT in Education and Training, International Conference on Computing in Arabic, and International Conference on Geocomputing (JCCO: TICET-ICCA-GECO), pp. 1–7. IEEE, Tunis, Piscataway (2018)
Bouamor, H., Oflazer, K., Habash, N.: A multidialectal parallel corpus of Arabic. In: 9th International Conference on Language Resources and Evaluation (LREC-2014), pp. 1240–1245. European Language Resources Association (ELRA), Reykjavik (2014)
Karmani, N.: Tunisian Arabic Customer’s Reviews Processing and Analysis for an Internet Supervision System (Doctoral dissertation). Sfax University, Sfax (2017)
Sayadi, K., Liwicki, M., Ingold, R., Bui, M.: Tunisian dialect and modern standard Arabic dataset for sentiment analysis: Tunisian election context. In: 2nd International Conference on Arabic Computational Linguistics, Konya (2016)
Jerbi, M., Achour, H., Souissi, E.: Sentiment analysis of code-switched tunisian dialect: Exploring RNN-based techniques. In: International Conference on Arabic Language Processing, pp. 122–131 (2019)
Mulki, H., Haddad, H., Bechikh Ali, C., Babaoglu, I.: Tunisian dialect sentiment analysis: a natural language processing-based approach. Computación y Sistemas 22(4), 1223–1232 (2018)
Mulki, H., Haddad, H., Gridach, M., Babaoglu, I.: Syntax-ignorant N-gram embeddings for sentiment analysis of Arabic dialects. In: 4th Arabic Natural Language Processing Workshop, pp. 30–39. Association for Computational Linguistics, Florence (2019)
TUNIZI dataset. https://github.com/chaymafourati/TUNIZI-Sentiment-Analysis-Tunisian-Arabizi-Dataset
TSAC dataset. https://github.com/fbougares/TSAC
Mikolov, T., Sutskever, I., Chen, K., Corrado, G., Dean, J.: distributed representations of words and phrases and their compositionality. In: Advances in Neural Information Processing Systems, vol. 26, pp. 3111–3119. Curran Associates Inc., Lake Tahoe (2013)
French Word Embeddings. http://fauconnier.github.io
Devlin, J., Chang, M., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers, pp. 4171–4186. Association for Computational Linguistics, Minneapolis (2019)
Author information
Authors and Affiliations
Corresponding authors
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2021 Springer Nature Switzerland AG
About this paper
Cite this paper
Messaoudi, A., Haddad, H., Ben HajHmida, M., Fourati, C., Ben Hamida, A. (2021). Learning Word Representations for Tunisian Sentiment Analysis. In: Djeddi, C., Kessentini, Y., Siddiqi, I., Jmaiel, M. (eds) Pattern Recognition and Artificial Intelligence. MedPRAI 2020. Communications in Computer and Information Science, vol 1322. Springer, Cham. https://doi.org/10.1007/978-3-030-71804-6_24
Download citation
DOI: https://doi.org/10.1007/978-3-030-71804-6_24
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-71803-9
Online ISBN: 978-3-030-71804-6
eBook Packages: Computer ScienceComputer Science (R0)