---
title: "Pre-trained Models or Feature Engineering: The Case of Dialectal"
description: "Published work on Arabic dialects reports results on corpora that differ in size, dialect coverage and… 49 references, cited by 2 papers here."
authors: ["Kathrein Abu Kwaik", "Stergios Chatzikyriakidis", "Simon Dobnik"]
year: 2022
venue: "Proceedinsg of the 5th Workshop on Open-Source Arabic Corpora and Processing Tools with Shared Tasks on Qur'an QA and Fine-Grained Hate Speech Detection"
source: "https://aclanthology.org/2022.osact-1.5/"
licence: "CC BY-NC 4.0 (ELRA, LREC proceedings)"
licence_url: "https://creativecommons.org/licenses/by-nc/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/kwaik-2022-pre-trained-models-or-feature/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/kwaik-2022-pre-trained-models-or-feature/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2022](https://md.research.elamur.ai/free/en/papers/2022/page/9/) / Pre-trained Models or Feature Engineering: The Case of Dialectal Arabic

# Pre-trained Models or Feature Engineering: The Case of Dialectal Arabic

**Authors:** [Kathrein Abu Kwaik](https://md.research.elamur.ai/free/en/authors/kathrein-abu-kwaik/), [Stergios Chatzikyriakidis](https://md.research.elamur.ai/free/en/authors/stergios-chatzikyriakidis/) and [Simon Dobnik](https://md.research.elamur.ai/free/en/authors/simon-dobnik/) · **Year:** 2022 · **Venue:** [Proceedinsg of the 5th Workshop on Open-Source Arabic Corpora and Processing Tools with Shared Tasks on Qur'an QA and Fine-Grained Hate Speech Detection](https://md.research.elamur.ai/free/en/venues/osact/) ([Workshop on Open-Source Arabic Corpora and Processing Tools with Shared Tasks 2022](https://md.research.elamur.ai/free/en/venues/osact/2022/)) · **Publisher:** [European Language Resources Association (ELRA)](https://md.research.elamur.ai/free/en/publishers/european-language-resources-association-elra/) · **Licence:** [CC BY-NC 4.0 (ELRA, LREC proceedings)](https://creativecommons.org/licenses/by-nc/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2022.osact-1.5/) · [PDF](https://aclanthology.org/2022.osact-1.5.pdf)

**Citations:** [2](https://md.research.elamur.ai/free/en/papers/kwaik-2022-pre-trained-models-or-feature/cited-by/) in our library, of the 149,439 papers whose bibliographies we read

## Summary
Published work on Arabic dialects reports results on corpora that differ in size, dialect coverage and quality, so it is hard to say whether neural models really beat classic classifiers on Dialectal Arabic. The authors run three families of models on the same datasets for two tasks, Dialect Identification and binary Sentiment Analysis:
- SVM and a dense classification layer over n-gram language-model features;
- LSTM networks over pre-trained AraVec word embeddings;
- BERT variants (Multilingual-BERT, Ara-BERT, Twitter-Arabic-BERT) with a classification layer on top.

The DI corpora are PADIC, SHAMI and MADAR-6. The SA corpora include ATSAD and are both balanced and skewed. Models are scored with accuracy, the Matthews correlation coefficient and a further measure.

Feature-engineered classifiers stay competitive with BERT. Transformers can pull ahead, but only when their pre-training text resembles the target text. LSTMs perform poorly throughout. The authors report state-of-the-art SA results on the corpora used. The study shows that cheap, transparent baselines remain worth running for low-resource, non-standard language varieties.

## Key points
- The three DI corpora differ in kind:
  - PADIC is parallel and built from transcribed Algerian phone conversations translated into other dialects. It has 6.400 sentences per dialect, covering five dialects (Algeria, Annaba, Tunisia, Palestine, Syria) plus MSA.
  - SHAMI holds 66.251 Levantine documents and is imbalanced: Syrian 37.760, Lebanese 10.830, Palestinian 10.643, Jordanian 7.018.
  - MADAR-6 is travel-domain parallel text. It has 10.000 documents each for Beirut, Cairo, Doha, Rabat, Tunisia and MSA.
- ATSAD is a balanced binary Twitter sentiment set from April 2019. Emojis served as seeds for collection. Experts labelled part of it, and self-training labelled the rest.
- MCC was chosen because it stays meaningful under class imbalance. It ranges from -1 to +1, with 0 meaning chance.
- Results:
  - Feature-based SVM classification competes with BERT models.
  - BERT's advantage depends on how close its pre-training data is to the task text.
  - LSTM with AraVec underperforms.
- The work is one of the few at the time applying BERT to Arabic Dialect Identification.

## Interesting ideas
- Hold the corpora fixed and swap only the model family, so that dataset differences cannot masquerade as method differences.
- Report MCC next to accuracy on skewed label sets, because accuracy can look good on a majority-class guesser while MCC exposes chance-level behaviour.
- Keep a strong, interpretable n-gram feature baseline beside pre-trained transformers, since on small, non-standard data it often closes most of the gap.
- Match pre-training text to target text, as a Twitter-trained BERT suits tweets better than a general one.
- Bootstrap labels cheaply by using surface signals (emojis) as seeds, hand-annotating a part, then extending the labels by self-training.

## For Mova

How these ideas could serve Mova, our small open language model — its files, stages and tests:

- **I1** (learn): When comparing the perceptron parser against gparse or any new component, always evaluate on identical splits, so a gain can be attributed to the method rather than the data.
- **I2** (learn): Add MCC to evaluations with skewed classes, such as speech-act or irony labels and rare dependency relations, as a built-in check against trivial predictors.
- **I3** (tokens): A feature-based tagger is a cheap, explainable reference for judging whether a heavier GPU model actually earns its cost on informal or dialectal English.
- **I4** (tree): When training gparse for social-media or dialectal English, prefer encoders and treebanks from the same register over generic ones.
- **I5** (learn): Weak cues plus a small gold core could seed silver data for sentiment or speech acts, with witness-parser or LLM agreement filtering the self-trained part.

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

📚 Shelves (2): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 18,614 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 17,965 works

🧭 Topics (1): [Semitic languages](https://md.research.elamur.ai/free/en/topics/semitic-languages/) · 3,066 works

## Cite

Cite as: Kathrein Abu Kwaik, Stergios Chatzikyriakidis and Simon Dobnik. 2022. Pre-trained Models or Feature Engineering: The Case of Dialectal Arabic. Proceedinsg of the 5th Workshop on Open-Source Arabic Corpora and Processing Tools with Shared Tasks on Qur'an QA and Fine-Grained Hate Speech Detection.

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@inproceedings{kwaik2022pre,
  title = {{Pre-trained Models or Feature Engineering: The Case of Dialectal Arabic}},
  author = {Kathrein Abu Kwaik, Stergios Chatzikyriakidis and Simon Dobnik},
  booktitle = {Proceedinsg of the 5th Workshop on Open-Source Arabic Corpora and Processing Tools with Shared Tasks on Qur'an QA and Fine-Grained Hate Speech Detection},
  year = {2022},
  url = {https://aclanthology.org/2022.osact-1.5/}
}
```

- [← previous Pre-trained Language Models' Interpretation of Evaluativity Implicature: Evidence from Gradable Adjectives Usage in Context](https://md.research.elamur.ai/free/en/papers/cong-2022-pre-trained-language-models-interpretation/)
- [next → Predicting the Proficiency Level of Nonnative Hebrew Authors](https://md.research.elamur.ai/free/en/papers/nguyen-2022-predicting-proficiency-level-nonnative-hebrew/)
- [↑ back to papers of 2022](https://md.research.elamur.ai/free/en/papers/2022/page/9/)

## References

49 references, 29 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Abdaoui, A., Berrimi, M., Oussalah, M., and Moussaoui, A. (2021). [Dziribert: a pre-trained language model for the algerian dialect](https://md.research.elamur.ai/free/en/papers/abdaoui-2021-dziribert-pre-trained-language-model/). arXiv preprint arXiv:2109.12346. [↗](https://arxiv.org/abs/2109.12346)
2. Abdul-Mageed, M., Diab, M., and Kübler, S. (2014). SAMAR: Subjectivity and sentiment analysis for Arabic social media. Computer Speech & Language, 28(1):20–37. [↗](https://doi.org/10.1016/j.csl.2013.03.001)
3. Abdullah, M., Hadzikadicy, M., and Shaikhz, S. (2018). SEDAT: Sentiment and Emotion Detection in Arabic Text Using CNN-LSTM Deep Learning. In 2018 17th IEEE International Conference on Machine Learning and Applications (ICMLA), pages 835–840. IEEE. [find](https://scholar.google.com/scholar?q=Abdullah%2C+M%2E%2C+Hadzikadicy%2C+M%2E%2C+and+Shaikhz%2C+S%2E+%282018%29%2E+SEDAT%3A+Sentiment+and+Emotion+Detection+in+Arabic+Text+Using+CNN%2DLSTM+Deep+Learning%2E+In+2018+17th+IEEE+International+Conference+on+Machine+Learnin)
4. Abu Kwaik, K. and Saad, M. K. (2019). [ArbDialectID at MADAR Shared Task 1: Language Modelling and Ensemble Learning for Fine Grained Arabic Dialect Identification](https://md.research.elamur.ai/free/en/papers/kwaik-2019-arbdialectid-madar-shared-task-1/). ArbDialectID at MADAR Shared Task 1: Language Modelling and Ensemble Learning for Fine Grained Arabic Dialect Identification, (Proceedings of the Fourth Arabic Natural Language Processing Workshop).
5. Al-Saqqa, S., Obeid, N., and Awajan, A. (2018). Sentiment Analysis for Arabic Text using Ensemble Learning. In 2018 IEEE/ACS 15th International Conference on Computer Systems and Applications (AICCSA), pages 1–7. IEEE. [find](https://scholar.google.com/scholar?q=Al%2DSaqqa%2C+S%2E%2C+Obeid%2C+N%2E%2C+and+Awajan%2C+A%2E+%282018%29%2E+Sentiment+Analysis+for+Arabic+Text+using+Ensemble+Learning%2E+In+2018+IEEE%2FACS+15th+International+Conference+on+Computer+Systems+and+Applications+%28AICCSA%29)
6. Ali, M. (2018). [Character level convolutional neural network for Arabic dialect identification](https://md.research.elamur.ai/free/en/papers/ali-2018-character-level-convolutional-neural-network/). In Proceedings of the Fifth Workshop on NLP for Similar Languages, Varieties and Dialects (VarDial 2018), pages 122–127.
7. Aly, M. and Atiya, A. (2013). [Labr: A large scale arabic book reviews dataset](https://md.research.elamur.ai/free/en/papers/aly-2013-labr-large-scale-arabic-book/). In Proceedings of the 51st Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers), volume 2, pages 494–498. [↗](https://doi.org/10.13140/2.1.3960.5761)
8. Antoun, W., Baly, F., and Hajj, H. (2020). [Arabert: Transformer-based model for arabic language understanding](https://md.research.elamur.ai/free/en/papers/antoun-2020-arabert-transformer-based-model-arabic/). arXiv preprint arXiv:2003.00104. [↗](https://arxiv.org/abs/2003.00104)
9. Baert, G., Gahbiche, S., Gadek, G., and Pauchet, A. (2020). [Arabizi language models for sentiment analysis](https://md.research.elamur.ai/free/en/papers/baert-2020-arabizi-language-models-sentiment-analysis/). In Proceedings of the 28th International Conference on Computational Linguistics, pages 592– 603, Barcelona, Spain (Online), December. International Committee on Computational Linguistics.
10. Baly, R., El-Khoury, G., Moukalled, R., Aoun, R., Hajj, H., Shaban, K. B., and El-Hajj, W. (2017). Comparative evaluation of sentiment analysis methods across arabic dialects. Procedia Computer Science, 117:266–273. [find](https://scholar.google.com/scholar?q=Baly%2C+R%2E%2C+El%2DKhoury%2C+G%2E%2C+Moukalled%2C+R%2E%2C+Aoun%2C+R%2E%2C+Hajj%2C+H%2E%2C+Shaban%2C+K%2E+B%2E%2C+and+El%2DHajj%2C+W%2E+%282017%29%2E+Comparative+evaluation+of+sentiment+analysis+methods+across+arabic+dialects%2E+Procedia+Computer+Scienc)
11. Beltagy, A., Wael, A., and ElSherief, O. (2020). [Arabic dialect identification using bert-based domain adaptation](https://md.research.elamur.ai/free/en/papers/beltagy-2020-arabic-dialect-identification-bert-based/). arXiv preprint arXiv:2011.06977. [↗](https://arxiv.org/abs/2011.06977)
12. Bouamor, H., Habash, N., Salameh, M., Zaghouani, W., Rambow, O., Abdulrahim, D., Obeid, O., Khalifa, S., Eryani, F., Erdmann, A., et al. (2018). The MADAR Arabic dialect corpus and lexicon. In Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018). [find](https://scholar.google.com/scholar?q=Bouamor%2C+H%2E%2C+Habash%2C+N%2E%2C+Salameh%2C+M%2E%2C+Zaghouani%2C+W%2E%2C+Rambow%2C+O%2E%2C+Abdulrahim%2C+D%2E%2C+Obeid%2C+O%2E%2C+Khalifa%2C+S%2E%2C+Eryani%2C+F%2E%2C+Erdmann%2C+A%2E%2C+et+al%2E+%282018%29%2E+The+MADAR+Arabic+dialect+corpus+and+lexicon%2E+In+Proceed)
13. Bouamor, H., Hassan, S., and Habash, N. (2019). [The MADAR shared task on Arabic fine-grained dialect identification](https://md.research.elamur.ai/free/en/papers/bouamor-2019-madar-shared-task-arabic-fine/). In Proceedings of the Fourth Arabic Natural Language Processing Workshop, pages 199–207.
14. Boughorbel, S., Jarray, F., and El-Anbari, M. (2017). Optimal classifier for imbalanced data using Matthews Correlation Coefficient metric. PloS one, 12(6):e0177678. [↗](https://doi.org/10.1371/journal.pone.0177678)
15. Chiang, D., Diab, M., Habash, N., Rambow, O., and Shareef, S. (2006). [Parsing Arabic dialects](https://md.research.elamur.ai/free/en/papers/chiang-2006-parsing-arabic-dialects/). In 11th Conference of the European Chapter of the Association for Computational Linguistics. [↗](https://doi.org/10.7916/d85t3tzg)
16. de Francony, G., Guichard, V., Joshi, P., Afli, H., and Bouchekif, A. (2019). [Hierarchical Deep Learning for Arabic Dialect Identification](https://md.research.elamur.ai/free/en/papers/francony-2019-hierarchical-deep-learning-arabic-dialect/). In Proceedings of the Fourth Arabic Natural Language Processing Workshop, pages 249–253.
17. Derczynski, L. (2016). Complementarity, F-score, and NLP Evaluation. In Proceedings of the Tenth International Conference on Language Resources and Evaluation (LREC’16), pages 261–266. [find](https://scholar.google.com/scholar?q=Derczynski%2C+L%2E+%282016%29%2E+Complementarity%2C+F%2Dscore%2C+and+NLP+Evaluation%2E+In+Proceedings+of+the+Tenth+International+Conference+on+Language+Resources+and+Evaluation+%28LREC%E2%80%9916%29%2C+pages+261%E2%80%93266%2E)
18. Devlin, J., Chang, M.-W., Lee, K., and Toutanova, K. (2018). [Bert: Pre-training of deep bidirectional transformers for language understanding](https://md.research.elamur.ai/free/en/papers/devlin-2019-bert-pre-training-deep-bidirectional/). arXiv preprint arXiv:1810.04805. [↗](https://arxiv.org/abs/1810.04805)
19. Diab, M. and Habash, N. (2014). Natural language processing of Arabic and its dialects. In Proceedings of the conference on empirical methods in natural language processing (EMNLP). Doha, Qatar, page 10. Citeseer. [find](https://scholar.google.com/scholar?q=Diab%2C+M%2E+and+Habash%2C+N%2E+%282014%29%2E+Natural+language+processing+of+Arabic+and+its+dialects%2E+In+Proceedings+of+the+conference+on+empirical+methods+in+natural+language+processing+%28EMNLP%29%2E+Doha%2C+Qatar%2C+page+)
20. Duwairi, R. M., Marji, R., Sha’ban, N., and Rushaidat, S. (2014). Sentiment analysis in Arabic tweets. In 2014 5th International Conference on Information and Communication Systems (ICICS), pages 1– 6. IEEE. [find](https://scholar.google.com/scholar?q=Duwairi%2C+R%2E+M%2E%2C+Marji%2C+R%2E%2C+Sha%E2%80%99ban%2C+N%2E%2C+and+Rushaidat%2C+S%2E+%282014%29%2E+Sentiment+analysis+in+Arabic+tweets%2E+In+2014+5th+International+Conference+on+Information+and+Communication+Systems+%28ICICS%29%2C+pages+1%E2%80%93+6)
21. Elawady, R. M., Barakat, S., and Elrashidy, N. M. (2014). Different feature selection for sentiment classification. International Journal of Information Science and Intelligent System, 3(1):137–150. [find](https://scholar.google.com/scholar?q=Elawady%2C+R%2E+M%2E%2C+Barakat%2C+S%2E%2C+and+Elrashidy%2C+N%2E+M%2E+%282014%29%2E+Different+feature+selection+for+sentiment+classification%2E+International+Journal+of+Information+Science+and+Intelligent+System%2C+3%281%29%3A137%E2%80%93150%2E)
22. Fares, Y., El-Zanaty, Z., Abdel-Salam, K., Ezzeldin, M., Mohamed, A., El-Awaad, K., and Torki, M. (2019). [Arabic Dialect Identification with Deep Learning and Hybrid Frequency Based Features](https://md.research.elamur.ai/free/en/papers/fares-2019-arabic-dialect-identification-deep-learning/). In Proceedings of the Fourth Arabic Natural Language Processing Workshop, pages 224–228.
23. Guellil, I., Saâdane, H., Azouaou, F., Gueni, B., and Nouvel, D. (2019). [Arabic natural language processing: An overview](https://md.research.elamur.ai/free/en/papers/guellil-2019-arabic-natural-language-processing-overview/). Journal of King Saud University-Computer and Information Sciences. [↗](https://doi.org/10.1016/j.jksuci.2019.02.006)
24. Habash, N., Rambow, O., and Kiraz, G. A. (2005). [Morphological analysis and generation for Arabic dialects](https://md.research.elamur.ai/free/en/papers/habash-2005-morphological-analysis-generation-arabic-dialects/). In Proceedings of the ACL Workshop on Computational Approaches to Semitic Languages, pages 17–24.
25. Heikal, M., Torki, M., and El-Makky, N. (2018). Sentiment analysis of Arabic Tweets using deep learning. Procedia Computer Science, 142:114–122. [find](https://scholar.google.com/scholar?q=Heikal%2C+M%2E%2C+Torki%2C+M%2E%2C+and+El%2DMakky%2C+N%2E+%282018%29%2E+Sentiment+analysis+of+Arabic+Tweets+using+deep+learning%2E+Procedia+Computer+Science%2C+142%3A114%E2%80%93122%2E)
26. Kwaik, K. A., Saad, M., Chatzikyriakidis, S., and Dobnik, S. (2018). [Shami: A corpus of levantine arabic dialects](https://md.research.elamur.ai/free/en/papers/kwaik-2018-shami-corpus-levantine-arabic-dialects/). In Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018).
27. Kwaik, K. A., Saad, M., Chatzikyriakidis, S., and Dobnik, S. (2019). LSTM-CNN Deep Learning Model for Sentiment Analysis of Dialectal Arabic. In International Conference on Arabic Language Processing, pages 108–121. Springer. [find](https://scholar.google.com/scholar?q=Kwaik%2C+K%2E+A%2E%2C+Saad%2C+M%2E%2C+Chatzikyriakidis%2C+S%2E%2C+and+Dobnik%2C+S%2E+%282019%29%2E+LSTM%2DCNN+Deep+Learning+Model+for+Sentiment+Analysis+of+Dialectal+Arabic%2E+In+International+Conference+on+Arabic+Language+Processing%2C)
28. Kwaik, K. A., Chatzikyriakidis, S., Dobnik, S., Saad, M., and Johansson, R. (2020). [An arabic tweets sentiment analysis dataset (atsad) using distant supervision and self training](https://md.research.elamur.ai/free/en/papers/kwaik-2020-arabic-tweets-sentiment-analysis-dataset/). In Proceedings of the 4th Workshop on Open-Source Arabic Corpora and Processing Tools, with a Shared Task on Offensive Language Detection, pages 1–8.
29. Matthews, B. W. (1975). Comparison of the predicted and observed secondary structure of T4 phage lysozyme. Biochimica et Biophysica Acta (BBA)-Protein Structure, 405(2):442–451. [↗](https://doi.org/10.1016/0005-2795(75)90109-9)
30. Meftouh, K., Harrat, S., Jamoussi, S., Abbas, M., and Smaili, K. (2015). [Machine translation experiments on PADIC: A parallel Arabic dialect corpus](https://md.research.elamur.ai/free/en/papers/meftouh-2015-machine-translation-experiments-padic-parallel/). In The 29th Pacific Asia conference on language, information and computation.
31. Meftouh, K., Abidi, K., Harrat, S., and Smaili, K. (2019). [The SMarT Classifier for Arabic Fine-Grained Dialect Identification](https://md.research.elamur.ai/free/en/papers/meftouh-2019-smart-classifier-arabic-fine-grained/).
32. Mishra, P. and Mujadia, V. (2019). [Arabic Dialect Identification for Travel and Twitter Text](https://md.research.elamur.ai/free/en/papers/mishra-2019-arabic-dialect-identification-travel-twitter/). In Proceedings of the Fourth Arabic Natural Language Processing Workshop, pages 234–238.
33. Mohammed, A. and Kora, R. (2019). Deep learning approaches for Arabic sentiment analysis. Social Network Analysis and Mining, 9(1):52. [↗](https://doi.org/10.1007/s13278-019-0596-4)
34. Mountassir, A., Benbrahim, H., and Berrada, I. (2012). An empirical study to address the problem of unbalanced data sets in sentiment classification. In 2012 IEEE international conference on systems, man, and cybernetics (SMC), pages 3298–3303. IEEE. [find](https://scholar.google.com/scholar?q=Mountassir%2C+A%2E%2C+Benbrahim%2C+H%2E%2C+and+Berrada%2C+I%2E+%282012%29%2E+An+empirical+study+to+address+the+problem+of+unbalanced+data+sets+in+sentiment+classification%2E+In+2012+IEEE+international+conference+on+systems%2C+)
35. Nabil, M., Aly, M., and Atiya, A. (2015). [Astd: Arabic sentiment tweets dataset](https://md.research.elamur.ai/free/en/papers/nabil-2015-astd-arabic-sentiment-tweets-dataset/). In Proceedings of the 2015 conference on empirical methods in natural language processing, pages 2515–2519. [↗](https://doi.org/10.60692/3ee2g-zjt73)
36. Obeid, O., Salameh, M., Bouamor, H., and Habash, N. (2019). [ADIDA: Automatic dialect identification for Arabic](https://md.research.elamur.ai/free/en/papers/obeid-2019-adida-automatic-dialect-identification-arabic/). In Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics (Demonstrations), pages 6–11, Minneapolis, Minnesota, June. Association for Computational Linguistics.
37. Omar, N., Albared, M., Al-Shabi, A. Q., and Al-Moslmi, T. (2013). Ensemble of classification algorithms for subjectivity and sentiment analysis of Arabic customers’ reviews. International Journal of Advancements in Computing Technology, 5(14):77. [find](https://scholar.google.com/scholar?q=Omar%2C+N%2E%2C+Albared%2C+M%2E%2C+Al%2DShabi%2C+A%2E+Q%2E%2C+and+Al%2DMoslmi%2C+T%2E+%282013%29%2E+Ensemble+of+classification+algorithms+for+subjectivity+and+sentiment+analysis+of+Arabic+customers%E2%80%99+reviews%2E+International+Journal+of+A)
38. Qwaider, C., Chatzikyriakidis, S., and Dobnik, S. (2019). [Can Modern Standard Arabic Approaches be used for Arabic Dialects? Sentiment Analysis as a Case Study](https://md.research.elamur.ai/free/en/papers/kwaik-2019-can-modern-standard-arabic-approaches/). In Proceedings of the 3rd Workshop on Arabic Corpus Linguistics, pages 40–50.
39. Ragab, A., Seelawi, H., Samir, M., Mattar, A., Al-Bataineh, H., Zaghloul, M., Mustafa, A., Talafha, B., Freihat, A. A., and Al-Natsheh, H. (2019). [Mawdoo3 AI at MADAR Shared Task: Arabic Fine-Grained Dialect Identification with Ensemble Learning](https://md.research.elamur.ai/free/en/papers/ragab-2019-mawdoo3-ai-madar-shared-task/). In Proceedings of the Fourth Arabic Natural Language Processing Workshop, pages 244–248.
40. Safaya, A., Abdullatif, M., and Yuret, D. (2020). [Kuisail at semeval-2020 task 12: Bert-cnn for offensive speech identification in social media](https://md.research.elamur.ai/free/en/papers/safaya-2020-kuisail-semeval-2020-task-12/). In Proceedings of the Fourteenth Workshop on Semantic Evaluation, pages 2054–2059.
41. Shoukry, A. and Rafea, A. (2012). Sentence-level Arabic sentiment analysis. In 2012 International Conference on Collaboration Technologies and Systems (CTS), pages 546–550. IEEE. [find](https://scholar.google.com/scholar?q=Shoukry%2C+A%2E+and+Rafea%2C+A%2E+%282012%29%2E+Sentence%2Dlevel+Arabic+sentiment+analysis%2E+In+2012+International+Conference+on+Collaboration+Technologies+and+Systems+%28CTS%29%2C+pages+546%E2%80%93550%2E+IEEE%2E)
42. Soliman, A. B., Eissa, K., and El-Beltagy, S. R. (2017). Aravec: A set of arabic word embedding models for use in arabic nlp. Procedia Computer Science, 117:256–265. [find](https://scholar.google.com/scholar?q=Soliman%2C+A%2E+B%2E%2C+Eissa%2C+K%2E%2C+and+El%2DBeltagy%2C+S%2E+R%2E+%282017%29%2E+Aravec%3A+A+set+of+arabic+word+embedding+models+for+use+in+arabic+nlp%2E+Procedia+Computer+Science%2C+117%3A256%E2%80%93265%2E)
43. Soumeur, A., Mokdadi, M., Guessoum, A., and Daoud, A. (2018). Sentiment Analysis of Users on Social Networks: Overcoming the challenge of the Loose Usages of the Algerian Dialect. Procedia computer science, 142:26–37. [find](https://scholar.google.com/scholar?q=Soumeur%2C+A%2E%2C+Mokdadi%2C+M%2E%2C+Guessoum%2C+A%2E%2C+and+Daoud%2C+A%2E+%282018%29%2E+Sentiment+Analysis+of+Users+on+Social+Networks%3A+Overcoming+the+challenge+of+the+Loose+Usages+of+the+Algerian+Dialect%2E+Procedia+computer+sc)
44. Suárez, P. J. O., Romary, L., and Sagot, B. (2020). [A monolingual approach to contextualized word embeddings for mid-resource languages](https://md.research.elamur.ai/free/en/papers/suarez-2020-monolingual-approach-contextualized-word-embeddings/). arXiv preprint arXiv:2006.06202. [↗](https://arxiv.org/abs/2006.06202)
45. Tachicart, R., Bouzoubaa, K., Aouragh, S. L., and Jaafa, H. (2017). Automatic identification of Moroccan colloquial Arabic. In International Conference on Arabic Language Processing, pages 201– 214. Springer. [find](https://scholar.google.com/scholar?q=Tachicart%2C+R%2E%2C+Bouzoubaa%2C+K%2E%2C+Aouragh%2C+S%2E+L%2E%2C+and+Jaafa%2C+H%2E+%282017%29%2E+Automatic+identification+of+Moroccan+colloquial+Arabic%2E+In+International+Conference+on+Arabic+Language+Processing%2C+pages+201%E2%80%93+214%2E+S)
46. Talafha, B., Ali, M., Za’ter, M. E., Seelawi, H., Tuffaha, I., Samir, M., Farhan, W., and Al-Natsheh, H. T. (2020). [Multi-Dialect Arabic BERT for Country-Level Dialect Identification](https://md.research.elamur.ai/free/en/papers/talafha-2020-multi-dialect-arabic-bert-country/). arXiv preprint arXiv:2007.05612. [↗](https://arxiv.org/abs/2007.05612)
47. Zaidan, O. F. and Callison-Burch, C. (2014). [Arabic dialect identification](https://md.research.elamur.ai/free/en/papers/zaidan-2014-arabic-dialect-identification/). Computational Linguistics, 40(1):171–202. [↗](https://doi.org/10.1162/coli_a_00169)
48. Zbib, R., Malchiodi, E., Devlin, J., Stallard, D., Matsoukas, S., Schwartz, R., Makhoul, J., Zaidan, O., and Callison-Burch, C. (2012). [Machine translation of Arabic dialects](https://md.research.elamur.ai/free/en/papers/zbib-2012-machine-translation-arabic-dialects/). In Proceedings of the 2012 conference of the north american chapter of the association for computational linguistics: Human language technologies, pages 49–59.
49. Zhang, C. and Abdul-Mageed, M. (2019). [No Army, No Navy: Bert Semi-supervised Learning of Arabic Dialects](https://md.research.elamur.ai/free/en/papers/zhang-2019-no-army-no-navy-bert/). In Proceedings of the Fourth Arabic Natural Language Processing Workshop, pages 279–284.

*Updated 1 November 2026*