---
title: "ArabGend: Gender Analysis and Inference on Arabic Twitter (2022)"
description: "The paper tackles the shortage of resources for analysing and predicting user gender on… 47.3 points. 36 references, cited by 2 papers here."
authors: ["Hamdy Mubarak", "Shammur Absar Chowdhury", "Firoj Alam"]
year: 2022
venue: "Proceedings of the Eighth Workshop on Noisy User-generated Text (W-NUT 2022)"
source: "https://aclanthology.org/2022.wnut-1.14/"
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/mubarak-2022-arabgend-gender-analysis-inference-arabic/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/mubarak-2022-arabgend-gender-analysis-inference-arabic/)

[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/7/) / ArabGend: Gender Analysis and Inference on Arabic Twitter

# ArabGend: Gender Analysis and Inference on Arabic Twitter

**Authors:** [Hamdy Mubarak](https://md.research.elamur.ai/free/en/authors/hamdy-mubarak/), [Shammur Absar Chowdhury](https://md.research.elamur.ai/free/en/authors/shammur-absar-chowdhury/) and [Firoj Alam](https://md.research.elamur.ai/free/en/authors/firoj-alam/) · **Year:** 2022 · **Venue:** [Proceedings of the Eighth Workshop on Noisy User-generated Text (W-NUT 2022)](https://md.research.elamur.ai/free/en/venues/wnut/) ([Workshop on Noisy User-generated Text 2022](https://md.research.elamur.ai/free/en/venues/wnut/2022/)) · **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/2022.wnut-1.14/) · [PDF](https://aclanthology.org/2022.wnut-1.14.pdf) · [OpenAlex](https://openalex.org/W4226021494)

**Citations:** 6 citations (OpenAlex, 2026-10-14) · [2](https://md.research.elamur.ai/free/en/papers/mubarak-2022-arabgend-gender-analysis-inference-arabic/cited-by/) in our library, of the 149,439 papers whose bibliographies we read

## Summary
The paper tackles the shortage of resources for analysing and predicting user gender on Arabic Twitter. The authors collected Arabic tweets in two separate phases. An earlier batch of about 4.35M tweets was used only to build a lexicon of gendered self-description words. A later batch of about 100M tweets was then labelled with that lexicon. Labels came from matching the first word of each profile description against the lexicon, followed by manual checking by a native speaker. The result is ArabGend: roughly 167K accounts with gender labels and about 92K user locations, released publicly.

On this data the authors compare male and female users along several lines: engagement, topics of interest, country presence and profession gaps. They also train gender classifiers on usernames, tweets, descriptions, profile pictures and friend networks. The strongest model, an SVM on character n-grams, reaches F1 82.1%, which is 47.3 points above the majority baseline. Its estimates of the female share of users closely match Twitter Ads figures. This makes the resource useful for demographic studies and for fairness audits of Arabic models.

## Key points
- The gender lexicon was built from about 10K unique profile-description first words. Words seen only once were dropped, leaving about 2,500. These were pre-tagged with Farasa and corrected by a native speaker, giving 713 entries (56% masculine, 44% feminine).
- The best classifier is an SVM over tf-idf weighted character [2-5] n-grams. It was chosen partly because it can be deployed with low compute, and it achieves F1 82.1%.
- Gender predicted from friends alone was weak, reaching 56% accuracy. The rule used was to label an account female when one third of its up to 100 friends were predicted female.
- Using the friend signal only when the text classifier is unsure raised F1 from 82.1% to 82.9%.
- A profile-image model reached only 64% accuracy, and 87% of its errors were women classified as men. The female share of users was about 20% by the authors' method versus 19% from Twitter Ads. A public demo is available at asad.qcri.org.

## Interesting ideas
- Gender is often marked explicitly in word forms, such as the Arabic Taa Marbouta suffix, but a curated exception list is still needed for unmarked or ambiguous words.
- Labels were bootstrapped from a highly reliable position (the first word of a self-description) using a seed lexicon. An automatic tool proposed the lexicon tags, and a human corrected both the lexicon and the final labels.
- The data used to build the lexicon was kept separate from the data it was applied to, to avoid selection bias.
- A slower, weaker signal (the friend network) was consulted only when the main classifier lacked confidence. This gave a small gain without paying its cost on every instance.
- Individual predictions were checked at the population level against independent aggregate sources such as Twitter Ads shares.

## For Mova

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

- **I1** (tokens): A small hand-checked list of paired gendered English nouns (actor/actress, waiter/waitress), with exceptions noted, could reliably fill the Gender morphological feature and support pronoun agreement.
- **I2** (learn): Silver data could likewise be harvested only from high-precision syntactic slots, with tool-proposed labels sent through human or LLM-teacher review before training.
- **I3** (learn): Rules or lexicons Mova induces itself should be derived on one corpus and evaluated on a disjoint one, which acts as a built-in control against circular gains.
- **I4** (tree): When the perceptron parser has low confidence on an arc, the sentence could be deferred to gparse or another witness parser, keeping the slow path rare.
- **I5** (world): Distributions of extracted entities and states across a corpus could be compared with known statistics from Wikidata as a sanity check when gold labels are missing.

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

## Institutions

- [Hamad bin Khalifa University](https://md.research.elamur.ai/free/en/universities/hamad-bin-khalifa-university/) — University, Doha, Qatar · 144 works · 14,175 citations

📚 Shelves (6): [🖥️ 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 · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 17,450 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 17,296 works · [🤝 Social Sciences](https://md.research.elamur.ai/free/en/shelves/social-sciences/) · 1,954 works · [🤝 Gender Studies](https://md.research.elamur.ai/free/en/shelves/social-sciences/gender-studies/) · 52 works

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

## Cite

Cite as: Hamdy Mubarak, Shammur Absar Chowdhury and Firoj Alam. 2022. ArabGend: Gender Analysis and Inference on Arabic Twitter. Proceedings of the Eighth Workshop on Noisy User-generated Text (W-NUT 2022).

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

```bibtex
@inproceedings{mubarak2022arabgend,
  title = {{ArabGend: Gender Analysis and Inference on Arabic Twitter}},
  author = {Hamdy Mubarak, Shammur Absar Chowdhury and Firoj Alam},
  booktitle = {Proceedings of the Eighth Workshop on Noisy User-generated Text (W-NUT 2022)},
  year = {2022},
  url = {https://aclanthology.org/2022.wnut-1.14/}
}
```

- [← previous YNU-HPCC at SemEval-2022 Task 6: Transformer-based Model for Intended Sarcasm Detection in English and Arabic](https://md.research.elamur.ai/free/en/papers/zheng-2022-ynu-hpcc-semeval-2022-task/)
- [next → Arabic Dialect Identification and Sentiment Classification using Transformer-based Models](https://md.research.elamur.ai/free/en/papers/attieh-2022-arabic-dialect-identification-sentiment-classification/)
- [↑ back to papers of 2022](https://md.research.elamur.ai/free/en/papers/2022/page/7/)

## References

36 references, 8 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Ahmed Abdelali, Hamdy Mubarak, Younes Samih, Sabit Hassan, and Kareem Darwish. 2021. [QADI: Arabic dialect identification in the wild](https://md.research.elamur.ai/free/en/papers/abdelali-2021-qadi-arabic-dialect-identification-wild/). In Proceedings of the Sixth Arabic Natural Language Processing Workshop, Kyiv, Ukraine (Virtual). Association for Computational Linguistics.
2. Kerstin Bischoff. 2012. We love rock’n’roll: analyzing and predicting friendship links in last. fm. In Proceedings of the 4th Annual ACM Web Science Conference, pages 47–56. [find](https://scholar.google.com/scholar?q=Kerstin+Bischoff%2E+2012%2E+We+love+rock%E2%80%99n%E2%80%99roll%3A+analyzing+and+predicting+friendship+links+in+last%2E+fm%2E+In+Proceedings+of+the+4th+Annual+ACM+Web+Science+Conference%2C+pages+47%E2%80%9356%2E)
3. Joymallya Chakraborty, Suvodeep Majumder, and Tim Menzies. 2021. Bias in machine learning software: why? how? what to do? In Proceedings of the 29th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering, pages 429–440. [find](https://scholar.google.com/scholar?q=Joymallya+Chakraborty%2C+Suvodeep+Majumder%2C+and+Tim+Menzies%2E+2021%2E+Bias+in+machine+learning+software%3A+why%3F+how%3F+what+to+do%3F+In+Proceedings+of+the+29th+ACM+Joint+Meeting+on+European+Software+Engineering+)
4. Xin Chen, Yu Wang, Eugene Agichtein, and Fusheng Wang. 2015. A comparative study of demographic attribute inference in twitter. In Proceedings of the International AAAI Conference on Web and Social Media, 1, pages 590–593, California, USA. AAAI. [find](https://scholar.google.com/scholar?q=Xin+Chen%2C+Yu+Wang%2C+Eugene+Agichtein%2C+and+Fusheng+Wang%2E+2015%2E+A+comparative+study+of+demographic+attribute+inference+in+twitter%2E+In+Proceedings+of+the+International+AAAI+Conference+on+Web+and+Social+Me)
5. Shammur Absar Chowdhury, Hamdy Mubarak, Ahmed Abdelali, Soon-gyo Jung, Bernard J. Jansen, and Joni Salminen. 2020. [A multi-platform Arabic news comment dataset for offensive language detection](https://md.research.elamur.ai/free/en/papers/chowdhury-2020-multi-platform-arabic-news-comment/). In Proceedings of the 12th Language Resources and Evaluation Conference, pages 6203–6212, Marseille, France. European Language Resources Association.
6. Morgane Ciot, Morgan Sonderegger, and Derek Ruths. 2013. Gender inference of Twitter users in non-English contexts. In Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing, pages 1136–1145. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Morgane+Ciot%2C+Morgan+Sonderegger%2C+and+Derek+Ruths%2E+2013%2E+Gender+inference+of+Twitter+users+in+non%2DEnglish+contexts%2E+In+Proceedings+of+the+2013+Conference+on+Empirical+Methods+in+Natural+Language+Proce)
7. Michael Conover, Jacob Ratkiewicz, Matthew Francisco, Bruno Gonçalves, Filippo Menczer, and Alessandro Flammini. 2011. Political polarization on twitter. In Proceedings of the International AAAI Conference on Web and Social Media, pages 89–96, Barcelona, Spain. AAAI. [find](https://scholar.google.com/scholar?q=Michael+Conover%2C+Jacob+Ratkiewicz%2C+Matthew+Francisco%2C+Bruno+Gon%C3%A7alves%2C+Filippo+Menczer%2C+and+Alessandro+Flammini%2E+2011%2E+Political+polarization+on+twitter%2E+In+Proceedings+of+the+International+AAAI+Confe)
8. Kareem Darwish and Hamdy Mubarak. 2016. [Farasa: A new fast and accurate Arabic word segmenter](https://md.research.elamur.ai/free/en/papers/darwish-2016-farasa-new-fast-accurate-arabic/). In Proceedings of the Tenth International Conference on Language Resources and Evaluation, LREC’16, pages 1070–1074, Portorož, Slovenia. European Language Resources Association (ELRA).
9. Shereen ElSayed and Mona Farouk. 2020. Gender identification for egyptian arabic dialect in twitter using deep learning models. Egyptian Informatics Journal, 21(3):159–167. [find](https://scholar.google.com/scholar?q=Shereen+ElSayed+and+Mona+Farouk%2E+2020%2E+Gender+identification+for+egyptian+arabic+dialect+in+twitter+using+deep+learning+models%2E+Egyptian+Informatics+Journal%2C+21%283%29%3A159%E2%80%93167%2E)
10. Nizar Habash, Houda Bouamor, and Christine Chung. 2019. [Automatic gender identification and reinflection in Arabic](https://md.research.elamur.ai/free/en/papers/habash-2019-automatic-gender-identification-reinflection-arabic/). In Proceedings of the First Workshop on Gender Bias in Natural Language Processing, pages 155–165. Association for Computational Linguistics.
11. Bassem Bsir and Mounir Zrigui. 2018. Enhancing deep learning gender identification with gated recurrent units architecture in social text. Computacion y Sistemas, 22:757–766. [find](https://scholar.google.com/scholar?q=Bassem+Bsir+and+Mounir+Zrigui%2E+2018%2E+Enhancing+deep+learning+gender+identification+with+gated+recurrent+units+architecture+in+social+text%2E+Computacion+y+Sistemas%2C+22%3A757%E2%80%93766%2E)
12. Sabit Hassan, Hamdy Mubarak, Ahmed Abdelali, and Kareem Darwish. 2021. [ASAD: Arabic social media analytics and unDerstanding](https://md.research.elamur.ai/free/en/papers/hassan-2021-asad-arabic-social-media-analytics/). In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: System Demonstrations, pages 113–118, Online. Association for Computational Linguistics.
13. John D. Burger, John Henderson, George Kim, and Guido Zarrella. 2011. [Discriminating gender on Twitter](https://md.research.elamur.ai/free/en/papers/burger-2011-discriminating-gender-twitter/). In Proceedings of the 2011 Conference on Empirical Methods in Natural Language Processing, Susan C Herring and Sharon Stoerger. 2014. Gender and (a) nonymity in computer-mediated communication. The handbook of language, gender, and sexuality, 2:567–586.
14. Shereen Hussein, Mona Farouk, and ElSayed Hemayed. 2019. Gender identification of egyptian dialect in twitter. Egyptian Informatics Journal, 20(2):109– 116. [find](https://scholar.google.com/scholar?q=Shereen+Hussein%2C+Mona+Farouk%2C+and+ElSayed+Hemayed%2E+2019%2E+Gender+identification+of+egyptian+dialect+in+twitter%2E+Egyptian+Informatics+Journal%2C+20%282%29%3A109%E2%80%93+116%2E)
15. Gil Levi and Tal Hassner. 2015. Age and gender classification using convolutional neural networks. In Proceedings of the IEEE conference on computer vision and pattern recognition workshops, pages 34– 42. [find](https://scholar.google.com/scholar?q=Gil+Levi+and+Tal+Hassner%2E+2015%2E+Age+and+gender+classification+using+convolutional+neural+networks%2E+In+Proceedings+of+the+IEEE+conference+on+computer+vision+and+pattern+recognition+workshops%2C+pages+34%E2%80%93)
16. Shoushan Li, Bin Dai, Zhengxian Gong, and Guodong Zhou. 2016. Semi-supervised gender classification with joint textual and social modeling. In Proceedings of COLING 2016, the 26th International Conference on Computational Linguistics: Technical Papers, pages 2092–2100. [find](https://scholar.google.com/scholar?q=Shoushan+Li%2C+Bin+Dai%2C+Zhengxian+Gong%2C+and+Guodong+Zhou%2E+2016%2E+Semi%2Dsupervised+gender+classification+with+joint+textual+and+social+modeling%2E+In+Proceedings+of+COLING+2016%2C+the+26th+International+Confer)
17. The COLING 2016 Organizing Committee. [find](https://scholar.google.com/scholar?q=The+COLING+2016+Organizing+Committee%2E)
18. W. Liu and D. Ruths. 2013. What’s in a name? using first names as features for gender inference in twitter. In AAAI Spring Symposium: Analyzing Microtext. [find](https://scholar.google.com/scholar?q=W%2E+Liu+and+D%2E+Ruths%2E+2013%2E+What%E2%80%99s+in+a+name%3F+using+first+names+as+features+for+gender+inference+in+twitter%2E+In+AAAI+Spring+Symposium%3A+Analyzing+Microtext%2E)
19. Yaguang Liu, Lisa Singh, and Zeina Mneimneh. 2021. A comparative analysis of classic and deep learning models for inferring gender and age of twitter users. In Proceedings of the International Conference on Deep Learning Theory and Applications. [find](https://scholar.google.com/scholar?q=Yaguang+Liu%2C+Lisa+Singh%2C+and+Zeina+Mneimneh%2E+2021%2E+A+comparative+analysis+of+classic+and+deep+learning+models+for+inferring+gender+and+age+of+twitter+users%2E+In+Proceedings+of+the+International+Confere)
20. Shervin Malmasi. 2014. A data-driven approach to studying given names and their gender and ethnicity associations. In Proceedings of the Australasian Language Technology Association Workshop, pages 145–149. [find](https://scholar.google.com/scholar?q=Shervin+Malmasi%2E+2014%2E+A+data%2Ddriven+approach+to+studying+given+names+and+their+gender+and+ethnicity+associations%2E+In+Proceedings+of+the+Australasian+Language+Technology+Association+Workshop%2C+pages+14)
21. Miller McPherson, Lynn Smith-Lovin, and James M Cook. 2001. Birds of a feather: Homophily in social networks. Annual review of sociology, 27(1):415– 444. [find](https://scholar.google.com/scholar?q=Miller+McPherson%2C+Lynn+Smith%2DLovin%2C+and+James+M+Cook%2E+2001%2E+Birds+of+a+feather%3A+Homophily+in+social+networks%2E+Annual+review+of+sociology%2C+27%281%29%3A415%E2%80%93+444%2E)
22. Alan Mislove, Sune Lehmann, Yong-Yeol Ahn, Jukka-Pekka Onnela, and James Rosenquist. 2011. Understanding the demographics of twitter users. In Proceedings of the International AAAI Conference on Web and Social Media, Barcelona, Spain. AAAI. [find](https://scholar.google.com/scholar?q=Alan+Mislove%2C+Sune+Lehmann%2C+Yong%2DYeol+Ahn%2C+Jukka%2DPekka+Onnela%2C+and+James+Rosenquist%2E+2011%2E+Understanding+the+demographics+of+twitter+users%2E+In+Proceedings+of+the+International+AAAI+Conference+on+Web+a)
23. Hamdy Mubarak and Kareem Darwish. 2014. [Using twitter to collect a multi-dialectal corpus of arabic](https://md.research.elamur.ai/free/en/papers/mubarak-2014-twitter-collect-multi-dialectal-corpus/). In Proceedings of the EMNLP 2014 Workshop on Arabic Natural Language Processing (ANLP), pages 1–7.
24. Juergen Mueller and Gerd Stumme. 2016. Gender inference using statistical name characteristics in twitter. In Proceedings of the The 3rd Multidisciplinary International Social Networks Conference on SocialInformatics 2016, Data Science 2016, pages 1–8. [find](https://scholar.google.com/scholar?q=Juergen+Mueller+and+Gerd+Stumme%2E+2016%2E+Gender+inference+using+statistical+name+characteristics+in+twitter%2E+In+Proceedings+of+the+The+3rd+Multidisciplinary+International+Social+Networks+Conference+on+S)
25. Arjun Mukherjee and Bing Liu. 2010. Improving gender classification of blog authors. In Proceedings of the 2010 Conference on Empirical Methods in Natural Language Processing, pages 207–217. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Arjun+Mukherjee+and+Bing+Liu%2E+2010%2E+Improving+gender+classification+of+blog+authors%2E+In+Proceedings+of+the+2010+Conference+on+Empirical+Methods+in+Natural+Language+Processing%2C+pages+207%E2%80%93217%2E+Associati)
26. Delip Rao, David Yarowsky, Abhishek Shreevats, and Manaswi Gupta. 2010. Classifying latent user attributes in twitter. In Proceedings of the 2nd International Workshop on Search and Mining User-Generated Contents, SMUC ’10, page 37–44, New York, NY, USA. Association for Computing Machinery. [find](https://scholar.google.com/scholar?q=Delip+Rao%2C+David+Yarowsky%2C+Abhishek+Shreevats%2C+and+Manaswi+Gupta%2E+2010%2E+Classifying+latent+user+attributes+in+twitter%2E+In+Proceedings+of+the+2nd+International+Workshop+on+Search+and+Mining+User%2DGenera)
27. Shigeyuki Sakaki, Yasuhide Miura, Xiaojun Ma, Keigo Hattori, and Tomoko Ohkuma. 2014. Twitter user gender inference using combined analysis of text and image processing. In Proceedings of the Third Workshop on Vision and Language, pages 54–61, Dublin, Ireland. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Shigeyuki+Sakaki%2C+Yasuhide+Miura%2C+Xiaojun+Ma%2C+Keigo+Hattori%2C+and+Tomoko+Ohkuma%2E+2014%2E+Twitter+user+gender+inference+using+combined+analysis+of+text+and+image+processing%2E+In+Proceedings+of+the+Third+Wo)
28. Fadi Salem. 2017. Social media and the internet of things. The Arab Social Media Report. [find](https://scholar.google.com/scholar?q=Fadi+Salem%2E+2017%2E+Social+media+and+the+internet+of+things%2E+The+Arab+Social+Media+Report%2E)
29. Erhan Sezerer, Ozan Polatbilek, and Selma Tekir. 2019. A Turkish dataset for gender identification of Twitter users. In Proceedings of the 13th Linguistic Annotation Workshop, pages 203–207. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Erhan+Sezerer%2C+Ozan+Polatbilek%2C+and+Selma+Tekir%2E+2019%2E+A+Turkish+dataset+for+gender+identification+of+Twitter+users%2E+In+Proceedings+of+the+13th+Linguistic+Annotation+Workshop%2C+pages+203%E2%80%93207%2E+Associati)
30. Juan Soler and Leo Wanner. 2016. A semi-supervised approach for gender identification. In Proceedings of the Tenth International Conference on Language Resources and Evaluation, pages 1282–1287. European Language Resources Association (ELRA). [find](https://scholar.google.com/scholar?q=Juan+Soler+and+Leo+Wanner%2E+2016%2E+A+semi%2Dsupervised+approach+for+gender+identification%2E+In+Proceedings+of+the+Tenth+International+Conference+on+Language+Resources+and+Evaluation%2C+pages+1282%E2%80%931287%2E+Europ)
31. Tomoki Taniguchi, Shigeyuki Sakaki, Ryosuke Shige-naka, Yukihiro Tsuboshita, and Tomoko Ohkuma. 2015. A weighted combination of text and image classifiers for user gender inference. In Proceedings of the Fourth Workshop on Vision and Language, pages 87–93. Association for Computational Linguistics. [find](https://scholar.google.com/scholar?q=Tomoki+Taniguchi%2C+Shigeyuki+Sakaki%2C+Ryosuke+Shige%2Dnaka%2C+Yukihiro+Tsuboshita%2C+and+Tomoko+Ohkuma%2E+2015%2E+A+weighted+combination+of+text+and+image+classifiers+for+user+gender+inference%2E+In+Proceedings+of+)
32. Tran Anh Tuan, Tien-Dung Cao, and Tram Truong-Huu. 2019. Dirac: A hybrid approach to customer demographics analysis for advertising campaigns. In 2019 6th NAFOSTED Conference on Information and Computer Science (NICS), pages 256–261. [find](https://scholar.google.com/scholar?q=Tran+Anh+Tuan%2C+Tien%2DDung+Cao%2C+and+Tram+Truong%2DHuu%2E+2019%2E+Dirac%3A+A+hybrid+approach+to+customer+demographics+analysis+for+advertising+campaigns%2E+In+2019+6th+NAFOSTED+Conference+on+Information+and+Comput)
33. Svitlana Volkova, Yoram Bachrach, Michael Armstrong, and Vijay Sharma. 2015. Inferring latent user properties from texts published in social media. In Twenty-Ninth AAAI Conference on Artificial Intelligence. [find](https://scholar.google.com/scholar?q=Svitlana+Volkova%2C+Yoram+Bachrach%2C+Michael+Armstrong%2C+and+Vijay+Sharma%2E+2015%2E+Inferring+latent+user+properties+from+texts+published+in+social+media%2E+In+Twenty%2DNinth+AAAI+Conference+on+Artificial+Intell)
34. Svitlana Volkova, Theresa Wilson, and David Yarowsky. 2013. [Exploring demographic language variations to improve multilingual sentiment analysis in social media](https://md.research.elamur.ai/free/en/papers/volkova-2013-exploring-demographic-language-variations-improve/). In Proceedings of the 2013 Conference on Empirical Methods in Natural Language Processing, pages 1815–1827. Association for Computational Linguistics.
35. Zijian Wang, Scott Hale, David Ifeoluwa Adelani, Przemyslaw Grabowicz, Timo Hartman, Fabian Flöck, and David Jurgens. 2019. Demographic inference and representative population estimates from multilingual social media data. In The world wide web conference, pages 2056–2067. [find](https://scholar.google.com/scholar?q=Zijian+Wang%2C+Scott+Hale%2C+David+Ifeoluwa+Adelani%2C+Przemyslaw+Grabowicz%2C+Timo+Hartman%2C+Fabian+Fl%C3%B6ck%2C+and+David+Jurgens%2E+2019%2E+Demographic+inference+and+representative+population+estimates+from+multiling)
36. Wajdi Zaghouani and Anis Charfi. 2018. Arap-tweet: A large multi-dialect Twitter corpus for gender, age and language variety identification. In Proceedings of the Eleventh International Conference on Language Resources and Evaluation (LREC 2018), Miyazaki, Japan. European Language Resources Association (ELRA). [find](https://scholar.google.com/scholar?q=Wajdi+Zaghouani+and+Anis+Charfi%2E+2018%2E+Arap%2Dtweet%3A+A+large+multi%2Ddialect+Twitter+corpus+for+gender%2C+age+and+language+variety+identification%2E+In+Proceedings+of+the+Eleventh+International+Conference+on+)

*Updated 2 November 2026*