---
title: "ONE — paper by Guellil et al. (2021) — summary and ideas"
description: "The authors instead propose one pipeline that yields one training corpus and one model architecture. 46 references, cited by 2 papers here."
authors: ["Imane Guellil", "Faical Azouaou", "Fodil Benali", "Hachani Ala-Eddine"]
year: 2021
venue: "Proceedings of the Eleventh Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis"
source: "https://aclanthology.org/2021.wassa-1.25/"
licence: "CC BY 4.0 (ACL Anthology)"
licence_url: "https://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/guellil-2021-one-one-model-one-algorithm/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/guellil-2021-one-one-model-one-algorithm/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2021](https://md.research.elamur.ai/free/en/papers/2021/page/8/) / ONE: Toward ONE model, ONE algorithm, ONE corpus dedicated to sentiment analysis of Arabic/Arabizi and its dialects

# ONE: Toward ONE model, ONE algorithm, ONE corpus dedicated to sentiment analysis of Arabic/Arabizi and its dialects

**Authors:** [Imane Guellil](https://md.research.elamur.ai/free/en/authors/imane-guellil/), [Faical Azouaou](https://md.research.elamur.ai/free/en/authors/faical-azouaou/), [Fodil Benali](https://md.research.elamur.ai/free/en/authors/fodil-benali/) and Hachani Ala-Eddine · **Year:** 2021 · **Venue:** [Proceedings of the Eleventh Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis](https://md.research.elamur.ai/free/en/venues/wassa/) ([Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis 2021](https://md.research.elamur.ai/free/en/venues/wassa/2021/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2021.wassa-1.25/) · [PDF](https://aclanthology.org/2021.wassa-1.25.pdf) · [OpenAlex](https://openalex.org/W3154509336)

**Citations:** 3 citations (OpenAlex, 2026-10-14) · [2](https://md.research.elamur.ai/free/en/papers/guellil-2021-one-one-model-one-algorithm/cited-by/) in our library, of the 149,439 papers whose bibliographies we read

## Summary
Arabic has at least 22 dialects plus MSA, and each can appear in Arabic script or in Latin-based Arabizi. Building a separate sentiment resource for every variety and script would mean roughly 46 resources for a single language. The authors instead propose one pipeline that yields one training corpus and one model architecture.

The pipeline works as follows:
- They collect Facebook comments from Algerian pages.
- They derive an Algerian sentiment lexicon by translating an English lexicon through the Glosbe API, then review it by hand.
- They label comments automatically with rules that account for emoticons, affixes, negation and contrast.
- They convert Arabizi test messages into Arabic script before classification.

Classification uses Word2vec features with shallow learners and fastText features with deep models.

The model is trained only on automatically labelled Algerian data, yet it beats or matches published results on Algerian, Tunisian and MSA/Egyptian test sets. Manually checking a small sample of the corpus raises scores further. The work suggests that one carefully built resource can transfer across related varieties.

## Key points
- The general algorithm, Algorithm 1, has seven steps:
  - manual seed resources (page IDs, emoticon and expression lists, prefixes/suffixes, negation and opposition terms);
  - comment extraction through RestFB;
  - automatic lexicon construction and manual lexicon review;
  - annotation;
  - Arabizi transliteration;
  - classification.
- Classification setup:
  - Word2vec uses CBOW and SG, 300 dimensions and a window of 10, feeding GNB, LR, RF, SGD and LinearSVC.
  - fastText feeds deep models such as Bi-LSTM.
- Results with the automatic corpus (Senti_Alg), F1:
  - 87.77 on Algerian Arabic-script test data and 76.13 on transliterated Arabizi;
  - 81.00 on SANA Alg, versus 75 reported by Rahab et al.;
  - 80.58 on ASTD/QCRI/ArTwitter, versus 79.62;
  - 91.59 on TSAC when its training and test sets are both transliterated.
- Manual audit: of 3,048 sampled messages (1,488 positive, 1,560 negative), 2,596 (85.17%) were labelled correctly.
- After the reviewed sample was corrected, F1 reached:
  - 90.16 on Senti Alg test Arabic;
  - 83.10 on manually transliterated Arabizi;
  - 81.75 on ASTD/QCRI/ARTwitter;
  - 80.69 on TSAC Test Tr, above the prior 78.

## Interesting ideas
- Only the most strongly polarised emoticons serve as automatic labels, which trades coverage for precision in distant supervision.
- Hand-checking a modest sample of an auto-labelled corpus both estimates its precision (about 85% here) and yields corrections that measurably lift downstream scores.
- Non-standard spellings are handled in two stages: generate many candidates (explicitly covering ambiguous vowels), then let a corpus language model choose among them.
- Polarity labelling goes beyond counting sentiment words: it applies explicit rules for negation, contrastive connectives and agglutinated affixes.
- A model built from a single variety (Algerian) is tested on neighbouring varieties (Tunisian, MSA/Egyptian), and a shared normalisation step closes much of the gap.

## For Mova

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

- **I1** (learn): Silver data could admit only the highest-confidence witness signals, such as unanimous parser agreement, rather than every weak cue.
- **I2** (learn): A fixed audited slice of each silver batch could report its true error rate and supply corrected items, acting as a cheap check on the silver pipeline.
- **I3** (tokens): Noisy English such as "gr8" or "thx" could be normalised the same way, with the tokenizer proposing candidates and a lexicon-backed scorer picking one transparently.
- **I4** (frames): Polarity in prag could flip under negation scope and shift its weight after contrast markers like "but", computed over the UD tree so each decision stays explainable.
- **I5** (tree): The parser could be trained on one English treebank variety and evaluated on other registers or dialects after a normalisation or conversion pass, to measure transfer rather than assume it.

*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 (4): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 16,667 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 16,194 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 16,039 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 15,891 works

🧭 Topics (2): [😊 Sentiment & emotion](https://md.research.elamur.ai/free/en/topics/sentiment-emotion/) · 972 works · [Semitic languages](https://md.research.elamur.ai/free/en/topics/semitic-languages/) · 2,908 works

## Cite

Cite as: Imane Guellil, Faical Azouaou, Fodil Benali and Hachani Ala-Eddine. 2021. ONE: Toward ONE model, ONE algorithm, ONE corpus dedicated to sentiment analysis of Arabic/Arabizi and its dialects. Proceedings of the Eleventh Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis.

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

```bibtex
@inproceedings{guellil2021one,
  title = {{ONE: Toward ONE model, ONE algorithm, ONE corpus dedicated to sentiment analysis of Arabic/Arabizi and its dialects}},
  author = {Imane Guellil, Faical Azouaou, Fodil Benali and Hachani Ala-Eddine},
  booktitle = {Proceedings of the Eleventh Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis},
  year = {2021},
  url = {https://aclanthology.org/2021.wassa-1.25/}
}
```

- [← previous Multilingual and Multilabel Emotion Recognition using Virtual Adversarial Training](https://md.research.elamur.ai/free/en/papers/gupta-2021-multilingual-multilabel-emotion-recognition-virtual/)
- [next → Overview of the Arabic Sentiment Analysis 2021 Competition at KAUST](https://md.research.elamur.ai/free/en/papers/alamro-2021-overview-arabic-sentiment-analysis-2021/)
- [↑ back to papers of 2021](https://md.research.elamur.ai/free/en/papers/2021/page/8/)

## References

46 references, 20 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Nawaf Abdulla, Salwa Mohammed, Mahmoud Al-Ayyoub, Mohammed Al-Kabi, et al. 2014. Automatic lexicon construction for arabic sentiment analysis. In Future Internet of Things and Cloud (Fi-Cloud), 2014 International Conference on, pages 547– 552. IEEE. • Automatic training corpus construction. • Using one language model trained for one dialect to MSA and either to other dialects. • Moreover, using the training corpus of one dialect to others (which is a case of transfer learning). • Stop handling Arabizi as it is. Transliter-taion is crucial for improving the results. [find](https://scholar.google.com/scholar?q=Nawaf+Abdulla%2C+Salwa+Mohammed%2C+Mahmoud+Al%2DAyyoub%2C+Mohammed+Al%2DKabi%2C+et+al%2E+2014%2E+Automatic+lexicon+construction+for+arabic+sentiment+analysis%2E+In+Future+Internet+of+Things+and+Cloud+%28Fi%2DCloud%29%2C+2014+I)
2. Nawaf A Abdulla, Nizar A Ahmed, Mohammed A Shehab, and Mahmoud Al-Ayyoub. 2013. Arabic sentiment analysis: Lexicon-based and corpus-based. In Applied Electrical Engineering and Computing Technologies (AEECT), 2013 IEEE Jordan Conference on, pages 1–6. IEEE. [find](https://scholar.google.com/scholar?q=Nawaf+A+Abdulla%2C+Nizar+A+Ahmed%2C+Mohammed+A+Shehab%2C+and+Mahmoud+Al%2DAyyoub%2E+2013%2E+Arabic+sentiment+analysis%3A+Lexicon%2Dbased+and+corpus%2Dbased%2E+In+Applied+Electrical+Engineering+and+Computing+Technologies+)
3. Mohamed Al-Badrashiny, Ramy Eskander, Nizar Habash, and Owen Rambow. 2014. [Automatic transliteration of romanized dialectal arabic](https://md.research.elamur.ai/free/en/papers/badrashiny-2014-automatic-transliteration-romanized-dialectal-arabic/). In Proceedings of the Eighteenth Conference on Computational Natural Language Learning, pages 30–38. analysis for arabizi text. In Information and Communication Systems (ICICS), 2016 7th International Conference on, pages 127–132. IEEE.
4. Samhaa R El-Beltagy. 2016. [Nileulex: A phrase and word level sentiment lexicon for egyptian and modern standard arabic](https://md.research.elamur.ai/free/en/papers/beltagy-2016-nileulex-phrase-word-level-sentiment/). In LREC.
5. Nora Al-Twairesh, Hend Al-Khalifa, AbdulMalik Al-Salman, and Yousef Al-Ohali. 2017. Arasenti-tweet: A corpus for arabic sentiment analysis of saudi tweets. Procedia Computer Science, 117:63– 72. [find](https://scholar.google.com/scholar?q=Nora+Al%2DTwairesh%2C+Hend+Al%2DKhalifa%2C+AbdulMalik+Al%2DSalman%2C+and+Yousef+Al%2DOhali%2E+2017%2E+Arasenti%2Dtweet%3A+A+corpus+for+arabic+sentiment+analysis+of+saudi+tweets%2E+Procedia+Computer+Science%2C+117%3A63%E2%80%93+72%2E)
6. Hady ElSahar and Samhaa R El-Beltagy. 2015. Building large arabic multi-domain resources for sentiment analysis. In International Conference on Intelligent Text Processing and Computational Linguistics, pages 23–34. Springer. [find](https://scholar.google.com/scholar?q=Hady+ElSahar+and+Samhaa+R+El%2DBeltagy%2E+2015%2E+Building+large+arabic+multi%2Ddomain+resources+for+sentiment+analysis%2E+In+International+Conference+on+Intelligent+Text+Processing+and+Computational+Linguistic)
7. Rahma M Alahmary, Hmood Z Al-Dossari, and Ahmed Z Emam. 2019. Sentiment analysis of saudi dialect using deep learning techniques. In 2019 International Conference on Electronics, Information, and Communication (ICEIC), pages 1–6. IEEE. [find](https://scholar.google.com/scholar?q=Rahma+M+Alahmary%2C+Hmood+Z+Al%2DDossari%2C+and+Ahmed+Z+Emam%2E+2019%2E+Sentiment+analysis+of+saudi+dialect+using+deep+learning+techniques%2E+In+2019+International+Conference+on+Electronics%2C+Information%2C+and+Comm)
8. A Aziz Altowayan and Lixin Tao. 2016. Word embeddings for arabic sentiment analysis. In Big Data (Big Data), 2016 IEEE International Conference on, pages 3820–3825. IEEE. [find](https://scholar.google.com/scholar?q=A+Aziz+Altowayan+and+Lixin+Tao%2E+2016%2E+Word+embeddings+for+arabic+sentiment+analysis%2E+In+Big+Data+%28Big+Data%29%2C+2016+IEEE+International+Conference+on%2C+pages+3820%E2%80%933825%2E+IEEE%2E)
9. Mohamed Aly and Amir Atiya. 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)
10. Mohammed Attia, Younes Samih, Ali El-Kahky, and Laura Kallmeyer. 2018. Multilingual multi-class sentiment classification using convolutional neural networks. In LREC. [find](https://scholar.google.com/scholar?q=Mohammed+Attia%2C+Younes+Samih%2C+Ali+El%2DKahky%2C+and+Laura+Kallmeyer%2E+2018%2E+Multilingual+multi%2Dclass+sentiment+classification+using+convolutional+neural+networks%2E+In+LREC%2E)
11. Gaétan Baert, Souhir Gahbiche, Guillaume Gadek, and Alexandre Pauchet. 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.
12. Fady Baly, Hazem Hajj, et al. 2020. [Arabert: Transformer-based model for arabic language understanding](https://md.research.elamur.ai/free/en/papers/antoun-2020-arabert-transformer-based-model-arabic/). In Proceedings of the 4th Workshop on Open-Source Arabic Corpora and Processing Tools, with a Shared Task on Offensive Language Detection, pages 9–15.
13. Naaima Boudad, Rdouan Faizi, Rachid Oulad Haj Thami, and Raddouane Chiheb. 2017. Sentiment analysis in arabic: A review of the literature. Ain Shams Engineering Journal. [↗](https://doi.org/10.1016/j.asej.2017.04.007)
14. Kareem Darwish. 2013. [Arabizi detection and conversion to arabic](https://md.research.elamur.ai/free/en/papers/darwish-2014-arabizi-detection-conversion-arabic/). arXiv preprint arXiv:1306.6755. [↗](https://arxiv.org/abs/1306.6755)
15. Kareem Darwish. 2014. [Arabizi detection and conversion to arabic](https://md.research.elamur.ai/free/en/papers/darwish-2014-arabizi-detection-conversion-arabic/). In Proceedings of the EMNLP 2014 Workshop on Arabic Natural Language Processing (ANLP), pages 217–224. [↗](https://doi.org/10.48550/arxiv.1306.6755)
16. Ali Farghaly and Khaled Shaalan. 2009. Arabic natural language processing: Challenges and solutions. ACM Transactions on Asian Language Information Processing (TALIP), 8(4):14. [↗](https://doi.org/10.1145/1644879.1644881)
17. Donia Gamal, Marco Alfonse, El-Sayed M El-Horbaty, and Abdel-Badeeh M Salem. 2019. Twitter benchmark dataset for arabic sentiment analysis. International Journal of Modern Education and Computer Science, 11(1):33. [↗](https://doi.org/10.5815/ijmecs.2019.01.04)
18. Badaroand Gilbert, Jundiand Hussein, Hajj Hazem, El-Hajj Wassim, and Habash Nizar. 2018. Arsel: A large scale arabic sentiment and emotion lexicon. [find](https://scholar.google.com/scholar?q=Badaroand+Gilbert%2C+Jundiand+Hussein%2C+Hajj+Hazem%2C+El%2DHajj+Wassim%2C+and+Habash+Nizar%2E+2018%2E+Arsel%3A+A+large+scale+arabic+sentiment+and+emotion+lexicon%2E)
19. Imane Guellil, Ahsan Adeel, Faical Azouaou, Fodil Benali, Ala-eddine Hachani, and Amir Hussain. 2018a. [Arabizi sentiment analysis based on transliteration and automatic corpus annotation](https://md.research.elamur.ai/free/en/papers/guellil-2018-arabizi-sentiment-analysis-based-transliteration/). In Proceedings of the 9th Workshop on Computational Approaches to Subjectivity, Sentiment and Social Media Analysis, pages 335–341. [↗](https://doi.org/10.60692/sr5gt-3hc61)
20. Imane Guellil, Ahsan Adeel, Faical Azouaou, and Amir Hussain. 2018b. [Sentialg: Automated corpus annotation for algerian sentiment analysis](https://md.research.elamur.ai/free/en/papers/guellil-2018-sentialg-automated-corpus-annotation-algerian/). arXiv preprint arXiv:1808.05079. [↗](https://arxiv.org/abs/1808.05079)
21. Imane Guellil, Faical Azouaou, Fodil Benali, Ala Eddine Hachani, and Marcelo Mendoza. 2020a. The role of transliteration in the process of arabizi translation/sentiment analysis. In Recent Advances in NLP: The Case of Arabic Language, pages 101–128. Springer. [↗](https://doi.org/10.1007/978-3-030-34614-0_6)
22. Imane Guellil, Faical Azouaou, Fodil Benali, ala-eddine Hachani, and Houda Saadane. 2018c. Approche hybride pour la translitération de l’arabizi algérien : une étude préliminaire. In Conference: 25e conférence sur le Traitement Automatique des Langues Naturelles (TALN), May 2018, Rennes, FranceAt: Rennes, France. [https://www.researchgate.net/](https://www.researchgate.net/) [↗](https://www.researchgate.net/)
23. Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 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)
24. Rehab M Duwairi, Mosab Alfaqeh, Mohammad Wardat, and Areen Alrabadi. 2016. Sentiment publication/326354578_Approche_Hybride_ pour_la_transliteration_de_l%27arabizi_ algerien_une_etude_preliminaire . [find](https://scholar.google.com/scholar?q=Rehab+M+Duwairi%2C+Mosab+Alfaqeh%2C+Mohammad+Wardat%2C+and+Areen+Alrabadi%2E+2016%2E+Sentiment+publication%2F326354578%5FApproche%5FHybride%5F+pour%5Fla%5Ftransliteration%5Fde%5Fl%2527arabizi%5F+algerien%5Fune%5Fetude%5Fpreliminaire+%2E)
25. Imane Guellil, Faical Azouaou, and Francisco Chiclana. 2020b. Arautosenti: Automatic annotation and new tendencies for sentiment classification of arabic messages. Social Network Analysis and Mining, 10(1):1–20. [↗](https://doi.org/10.1007/s13278-020-00688-x)
26. Imane Guellil, Faical Azouaou, Houda Saâdane, and Nasredine Semmar. 2017. Une approche fondée sur les lexiques d’analyse de sentiments du dialecte algérien. [find](https://scholar.google.com/scholar?q=Imane+Guellil%2C+Faical+Azouaou%2C+Houda+Saa%CC%82dane%2C+and+Nasredine+Semmar%2E+2017%2E+Une+approche+fonde%CC%81e+sur+les+lexiques+d%E2%80%99analyse+de+sentiments+du+dialecte+alge%CC%81rien%2E)
27. Saif M Mohammad, Mohammad Salameh, and Svetlana Kiritchenko. 2016b. How translation alters sentiment. Journal of Artificial Intelligence Research, 55:95–130. [↗](https://doi.org/10.1613/jair.4787)
28. Imane Guellil, Faical Azouaou, and Alessandro Valitutti. 2019a. English vs arabic sentiment analysis: A survey presenting 100 work studies, resources and tools. In 2019 IEEE/ACS 16th International Conference on Computer Systems and Applications (AICCSA), pages 1–8. IEEE. [find](https://scholar.google.com/scholar?q=Imane+Guellil%2C+Faical+Azouaou%2C+and+Alessandro+Valitutti%2E+2019a%2E+English+vs+arabic+sentiment+analysis%3A+A+survey+presenting+100+work+studies%2C+resources+and+tools%2E+In+2019+IEEE%2FACS+16th+International+Con)
29. Ahmed Mourad and Kareem Darwish. 2013. [Subjectivity and sentiment analysis of modern standard arabic and arabic microblogs](https://md.research.elamur.ai/free/en/papers/mourad-2013-subjectivity-sentiment-analysis-modern-standard/). In Proceedings of the 4th workshop on computational approaches to subjectivity, sentiment and social media analysis, pages 55–64.
30. Imane Guellil, Houda Saâdane, Faical Azouaou, Billel Gueni, and Damien Nouvel. 2019b. [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)
31. Mahmoud Nabil, Mohamed Aly, and Amir Atiya. 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)
32. Nizar Y Habash. 2010. Introduction to arabic natural language processing. Synthesis Lectures on Human Language Technologies, 3(1):1–187. [↗](https://doi.org/10.1007/978-3-031-02139-8)
33. Salima Harrat, Karima Meftouh, and Kamel Smaı̈li. 2017. Maghrebi arabic dialect processing: an overview. In ICNLSSP 2017-International Conference on Natural Language, Signal and Speech Processing. [find](https://scholar.google.com/scholar?q=Salima+Harrat%2C+Karima+Meftouh%2C+and+Kamel+Sma%C4%B1%CC%88li%2E+2017%2E+Maghrebi+arabic+dialect+processing%3A+an+overview%2E+In+ICNLSSP+2017%2DInternational+Conference+on+Natural+Language%2C+Signal+and+Speech+Processing%2E)
34. Alexander Hogenboom, Daniella Bal, Flavius Frasincar, Malissa Bal, Franciska de Jong, and Uzay Kaymak. 2013. Exploiting emoticons in sentiment analysis. In Proceedings of the 28th Annual ACM Symposium on Applied Computing, pages 703– 710. ACM. [find](https://scholar.google.com/scholar?q=Alexander+Hogenboom%2C+Daniella+Bal%2C+Flavius+Frasincar%2C+Malissa+Bal%2C+Franciska+de+Jong%2C+and+Uzay+Kaymak%2E+2013%2E+Exploiting+emoticons+in+sentiment+analysis%2E+In+Proceedings+of+the+28th+Annual+ACM+Symposium)
35. Guellil Imane, Darwish Kareem, and Azouaou Faical. 2019. A set of parameters for automatically annotating a sentiment arabic corpus. International Journal of Web Information Systems. [↗](https://doi.org/10.1108/ijwis-03-2019-0008)
36. Shereen Khoja and Roger Garside. 1999. Stemming arabic text. Lancaster, UK, Computing Department, Lancaster University. [find](https://scholar.google.com/scholar?q=Shereen+Khoja+and+Roger+Garside%2E+1999%2E+Stemming+arabic+text%2E+Lancaster%2C+UK%2C+Computing+Department%2C+Lancaster+University%2E)
37. M’hamed Mataoui, Omar Zelmati, and Madiha Boumechache. 2016. A proposed lexicon-based sentiment analysis approach for the vernacular algerian arabic. Research in Computing Science, 110:55–70. [↗](https://doi.org/10.13053/rcs-110-1-5)
38. Jonathan May, Yassine Benjira, and Abdessamad Echihabi. 2014. [An arabizi-english social media statistical machine translation system](https://md.research.elamur.ai/free/en/papers/may-2014-arabizi-english-social-media-statistical/). In Proceedings of the 11th Conference of the Association for Machine Translation in the Americas, pages 329–341.
39. Salima Medhaffar, Fethi Bougares, Yannick Esteve, and Lamia Hadrich-Belguith. 2017. [Sentiment analysis of tunisian dialects: Linguistic ressources and experiments](https://md.research.elamur.ai/free/en/papers/medhaffar-2017-sentiment-analysis-tunisian-dialects-linguistic/). In Proceedings of the Third Arabic Natural Language Processing Workshop, pages 55–61.
40. Saif Mohammad, Mohammad Salameh, and Svetlana Kiritchenko. 2016a. [Sentiment lexicons for arabic social media](https://md.research.elamur.ai/free/en/papers/mohammad-2016-sentiment-lexicons-arabic-social-media/). In LREC.
41. Alexander Pak and Patrick Paroubek. 2010. [Twitter as a corpus for sentiment analysis and opinion mining](https://md.research.elamur.ai/free/en/papers/pak-2010-twitter-as-corpus-sentiment-analysis/).
42. Matthew E Peters, Mark Neumann, Mohit Iyyer, Matt Gardner, Christopher Clark, Kenton Lee, and Luke Zettlemoyer. 2018. [Deep contextualized word representations](https://md.research.elamur.ai/free/en/papers/peters-2018-deep-contextualized-word-representations/). arXiv preprint arXiv:1802.05365. [↗](https://arxiv.org/abs/1802.05365)
43. Hichem Rahab, Abdelhafid Zitouni, and Mahied-dine Djoudi. 2019. Sana: Sentiment analysis on newspapers comments in algeria. Journal of King Saud University-Computer and Information Sciences. [↗](https://doi.org/10.1016/j.jksuci.2019.04.012)
44. Mohammad Salameh, Saif Mohammad, and Svetlana Kiritchenko. 2015. [Sentiment after translation: A case-study on arabic social media posts](https://md.research.elamur.ai/free/en/papers/salameh-2015-sentiment-after-translation-case-study/). In Proceedings of the 2015 conference of the North American chapter of the association for computational linguistics: Human language technologies, pages 767– 777.
45. Marlies van der Wees, Arianna Bisazza, and Christof Monz. 2016. [A simple but effective approach to improve arabizi-to-english statistical machine translation](https://md.research.elamur.ai/free/en/papers/wees-2016-simple-but-effective-approach-improve/). In Proceedings of the 2nd Workshop on Noisy User-generated Text (WNUT), pages 43–50.
46. Payal Yadav and Dhatri Pandya. 2017. Sentire-view: Sentiment analysis based on text and emoticons. In Innovative Mechanisms for Industry Applications (ICIMIA), 2017 International Conference on, pages 467–472. IEEE. [find](https://scholar.google.com/scholar?q=Payal+Yadav+and+Dhatri+Pandya%2E+2017%2E+Sentire%2Dview%3A+Sentiment+analysis+based+on+text+and+emoticons%2E+In+Innovative+Mechanisms+for+Industry+Applications+%28ICIMIA%29%2C+2017+International+Conference+on%2C+pages+)

*Updated 1 November 2026*