Hybrid RNN-LSTM Architecture for Sentiment Analysis of Algerian Dialectal Social Media Content
DOI:
https://doi.org/10.58190/ijamec.2025.128Keywords:
Sentiment Analysis Applications , Natural Language ProcessingAbstract
Sentiment analysis in under-resourced dialects like Algerian Arabic (Darija) presents unique challenges due to code-switching, informal orthography, and cultural-linguistic nuances. This study addresses the binary sentiment classification task using a hybrid Recurrent Neural Network–Long Short-Term Memory (RNN-LSTM) architecture, designed to effectively capture sequential dependencies and long-term contextual information. The model is trained on DZSentiA, a curated dataset of annotated Algerian dialect social media posts, and achieves strong performance with an accuracy of 84.7%, an F1-score of 84.45%, a recall of 82,75%, and a precision of 84.7%. These results surpass several baseline methods, highlighting the potential of deep learning approaches in low-resource dialectal settings. This work contributes to dialect-specific Natural Language Processing (NLP) by demonstrating the feasibility and effectiveness of deep models in sentiment detection for Algerian Darija, and supports the broader goal of developing culturally aware tools for online discourse analysis.
Downloads
References
[1] M. Abdaoui, M. Berrimi, and A. Oussalah-Moussaoui, “Dziribert: A pre-trained language model for the Algerian dialect,” arXiv preprint, arXiv:2109.12346, 2021.
[2] A. Abdelli, F. Guerrouf, O. Tibermacine, and B. Abdelli, “Sentiment Analysis of Arabic Algerian Dialect Using a Supervised Method,” in Proc. Int. Conf. Intelligent Systems and Advanced Computing Sciences (ISACS), Taza, Morocco, 2019, pp. 1–6.
[3] D. Boughareb, R. Boughareb, N. Guerri, and H. Seridi, “FindLoc: A Sentiment Analysis-Based Recommender System,” in Proc. 3rd Int. Conf. Computing and Information Technology (ICCIT), 2023, doi: 10.1109/ICCIT58132.2023.10273931.
[4] D. Boughareb, R. Boughareb, S. Hallaci, M. R. E. Boukherouba, and H. Seridi, “Addressing the Complexity of Dialectal Arabic: An Enhanced Encoder-Decoder Ensemble Approach for Optimized Sentiment Analysis,” ACM Trans. Asian Low-Resour. Lang. Inf. Process., vol. 24, no. 6, Art. no. 58, pp. 1–21, Jun. 2025, doi: 10.1145/3735972.
[5] A. Dahou et al., “A Survey on Dialect Arabic Processing and Analysis: Recent Advances and Future Trends,” ACM Trans. Asian Low-Resour. Lang. Inf. Process., Just Accepted, Jul. 2025, doi: 10.1145/3747290.
[6] A. Habberrih and M. A. Abuzaraida, “Sentiment analysis of Arabic dialects: A review study,” in Proc. Int. Conf. Computing and Informatics (ICOCI 2023), Lecture Notes in Computer Science, vol. 2001, pp. 269–280, Springer, 2024, doi: 10.1007/978-981-99-9589-9_11.
[7] M. E.-D. M. Hussein, “A survey on sentiment analysis challenges,” J. King Saud Univ. - Comput. Inf. Sci., vol. 29, no. 4, pp. 512–523, 2017, doi: 10.1016/j.jksuci.2016.03.004.
[8] A. C. Mazari and A. Djeffal, “Sentiment analysis of Algerian dialect using machine learning and deep learning with word2vec,” Informatica, vol. 46, no. 6, 2022, doi: 10.31449/inf.v46i6.3340.
[9] S. Brachemi-Meftah, F. Barigou, A. Djendara, and O. Zaoui, “Impact of Dimensionality Reduction on Sentiment Analysis of Algerian Dialect,” in Proc. IEEE 9th Int. Conf. Sciences of Electronics, Technologies of Information and Telecommunications (SETIT), Hammamet, Tunisia, 2022, pp. 433–440, doi: 10.1109/SETIT54465.2022.9875532.
[10] D. P. Kingma and J. L. Ba, “Adam: A method for stochastic optimization,” presented at the 3rd Int. Conf. Learning Representations (ICLR), San Diego, CA, USA, 2015.
[11] L. Moudjari and K. Akli-Astouati, “An Experimental Study on Sentiment Classification of Algerian Dialect Texts,” Procedia Comput. Sci., vol. 176, pp. 1151–1159, 2020, doi: 10.1016/j.procs.2020.09.111.
[12] H. Rahab, A. Zitouni, and M. Djoudi, “SANA: Sentiment analysis on newspapers comments in Algeria,” J. King Saud Univ. - Comput. Inf. Sci., vol. 33, no. 7, pp. 899–907, 2021, doi: 10.1016/j.jksuci.2019.04.012.
[13] L. Ouchene and S. Bessou, “Sentiment analysis for Algerian Dialect tweets,” in Proc. 14th Int. Conf. Computational Intelligence and Communication Networks (CICN), Al-Khobar, Saudi Arabia, 2022, pp. 235–239, doi: 10.1109/CICN56167.2022.10008314.
[14] S. Klouche, M. Benslimane, and N. Mahammed, “Sentiment Analysis of Algerian Dialect Using a Deep Learning Approach,” in Artificial Intelligence and Its Applications, AIAP 2021, Lecture Notes in Networks and Systems, vol. 413, Springer, Cham, 2022, doi: 10.1007/978-3-030-96311-8_12.
[15] M. Kara, A. Laouid, A. Bounceur, and O. Aldabbas, “Arabic Opinion Mining Using Machine Learning Techniques: Algerian Dialect as a Case of Study,” Preprints.org, 2023, doi: 10.20944/preprints202301.0443.v1.
[16] M. Abdul-Mageed, A. Elmadany, and E. M. B. Nagoudi, “UL2T: Detecting linguistic complexity in Arabic social media,” in Proc. 12th Lang. Resources and Evaluation Conf. (LREC), 2020, pp. 7157–7166.
[17] R. Al-Sabbagh and R. Girju, “A supervised POS tagger for written Arabic social networking corpora,” in Proc. 2012 Joint Conf. Empirical Methods in Natural Language Processing and Computational Natural Language Learning (EMNLP-CoNLL), 2012, pp. 494–504.
[18] S. L. Blodgett, S. Barocas, H. Daumé III, and H. Wallach, “Language (technology) is power: A critical survey of ‘bias’ in NLP,” in Proc. 58th Annu. Meeting of the Assoc. for Comput. Linguistics (ACL), 2020, pp. 5454–5476.
[19] H. Bouamor, N. Habash, and K. Oflazer, “The MADAR Arabic dialect corpus and lexicon,” in Proc. 2019 Conf. Empirical Methods in Natural Language Processing and 9th Int. Joint Conf. Natural Language Processing (EMNLP-IJCNLP), 2019, pp. 1297–1303.
[20] N. Habash, R. Eskander, and A. Hawwari, “A morphological analyzer for Egyptian Arabic,” in Proc. 2012 Workshop Free/Open-Source Arabic Corpora and Corpora Processing Tools, 2012, pp. 1–9.
[21] S. Kiritchenko, X. Zhu, and S. M. Mohammad, “Sentiment analysis of short informal texts,” J. Artif. Intell. Res., vol. 50, pp. 723–762, 2014.
[22] A. Mena, Digital Activism and Conflict in Algeria: Youth, Social Media, and the Hirak Movement, Cham, Switzerland: Palgrave Macmillan, 2020.
[23] H. Mubarak, K. Darwish, and W. Magdy, “Arabic dialect identification for hate speech detection: A preliminary study,” in Proc. 4th Workshop on Open-Source Arabic Corpora and Processing Tools (OSACT), 2020, pp. 20–27.
[24] A. Pak and P. Paroubek, “Twitter as a corpus for sentiment analysis and opinion mining,” in Proc. 7th Int. Conf. Language Resources and Evaluation (LREC), 2010, pp. 1320–1326.
[25] H. Saadane and N. Habash, “A conventional orthography for Algerian Arabic,” in Proc. 2nd Workshop on Arabic Natural Language Processing (WANLP), 2015, pp. 69–77.
[26] M. Sap, D. Card, S. Gabriel, Y. Choi, and N. A. Smith, “Ethical challenges in NLP: The role of value pluralism, power, and inclusivity,” in Proc. 2022 ACM Conf. Fairness, Accountability, and Transparency (FAccT), 2022, pp. 1–13.
[27] A. Schmidt and M. Wiegand, “A survey on hate speech detection using natural language processing,” in Proc. 5th Int. Workshop Natural Language Processing for Social Media (SocialNLP), 2017, pp. 1–10.
[28] O. F. Zaidan and C. Callison-Burch, “Arabic dialect identification,” Comput. Linguist., vol. 40, no. 1, pp. 171–202, 2014.
[29] S. Hochreiter and J. Schmidhuber, “Long short-term memory,” Neural Comput., vol. 9, no. 8, pp. 1735–1780, 1997, doi: 10.1162/neco.1997.9.8.1735.
[30] J. L. Elman, “Finding structure in time,” Cogn. Sci., vol. 14, no. 2, pp. 179–211, 1990, doi: 10.1207/s15516709cog1402_1.
[31] I. Goodfellow, Y. Bengio, and A. Courville, Deep Learning. Cambridge, MA: MIT Press, 2016.
Downloads
Published
Issue
Section
License
Copyright (c) 2025 International Journal of Applied Methods in Electronics and Computers
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
