About ASAD



ASAD: Arabic Social media Analytics and unDerstanding is a suite of systems for analyzing Arabic Twitter content. The modules we provide are Dialect Identification, Sentiment Analysis, Emotion Detection, News Category detection, Offensive Language Detection, Hate Speech Detection, Adult Content Detection, Spam Detection, Location to Country, Name to Country, and Gender Classification. More functions will be added.
These models are available via web demo where users can access the models and also upload files for classification. The modules are also accessible via webapi.

...
Hamdy Mubarak
Principal Software Engineer
...
Dr. Ahmed Abdelali
Principal Software Engineer
...
Dr. Kareem Darwish
Principal Scientist
...
Sabit Hassan
Research Assistant
...
Dr. Younes Samih
PostDoc Researcher
...
Dr. Shammur Chowdhury
PostDoc Researcher

Collaborators

...
Dr. Walid Magdy
University of Edinburgh (UK)
...
Ammar Rashed
Özyeğin University (Turkey)
...
Dr. Abdelrahim Elmadany
Jazan University (KSA)

Publications



  • Hassan, S., Mubarak, H., Abdelali, A., & Darwish, K. (2021, April). ASAD: Arabic Social media Analytics and unDerstanding In Proceedings of the 16th Conference of the European Chapter of the Association for Computational Linguistics: System Demonstrations (pp.113-118)
  • Mubarak, H., Hassan, S., & Abdealali, A. (2021, April). Adult Content Detection on Arabic Twitter: Analysis and Experiments In Proceedings of the Sixth Arabic Natural Language Processing Workshop (pp.136-144)
  • Mubarak, H., & Hassan, S. (2021, April). UL2C: Mapping User Locations to Countries on Arabic Twitter. In Proceedings of the Sixth Arabic Natural Language Processing Workshop (pp.145--153)
  • Mubarak, H., Abdelali, A., Hassan, S., & Darwish, K. (2020, October). Spam Detection on Arabic Twitter. In International Conference on Social Informatics (pp. 237-251). Springer, Cham.
  • Hassan, S., Samih, Y., Mubarak, H., Abdelali, A., Rashed, A., & Chowdhury, S. A. (2020, May). ALT submission for OSACT shared task on offensive language detection. In Proceedings of the 4th Workshop on Open-Source Arabic Corpora and Processing Tools, with a Shared Task on Offensive Language Detection (pp. 61-65).
  • Chowdhury, S. A., Mubarak, H., Abdelali, A., Jung, S. G., Jansen, B. J., & Salminen, J. (2020, May). A multi-platform arabic news comment dataset for offensive language detection. In Proceedings of The 12th Language Resources and Evaluation Conference (pp. 6203-6212).
  • Abdelali, A., Mubarak, H., Samih, Y., Hassan, S., & Darwish, K. (2020). Arabic Dialect Identification in the Wild. arXiv preprint arXiv:2005.06557.
  • Hassan, S., Samih, Y., Mubarak, H., & Abdelali, A. 2020. ALT at SemEval-2020 Task 12: Arabic and English offensive language identification in social media. In Proceedings of the International Workshop on Semantic Evaluation (SemEval).
  • Zampieri, M., Nakov, P., Rosenthal, S., Atanasova, P., Karadzhov, G., Mubarak, H., ... & Çöltekin, Ç. (2020). SemEval-2020 task 12: Multilingual offensive language identification in social media (OffensEval 2020). arXiv preprint arXiv:2006.07235.
  • Mubarak, H., Rashed, A., Darwish, K., Samih, Y., & Abdelali, A. (2020). Arabic offensive language on twitter: Analysis and experiments. arXiv preprint arXiv:2004.02192.
  • Mubarak, H., Darwish, K., Magdy, W., Elsayed, T., & Al-Khalifa, H. (2020, May). Overview of OSACT4 Arabic Offensive Language Detection Shared Task. In Proceedings of the 4th Workshop on Open-Source Arabic Corpora and Processing Tools, with a Shared Task on Offensive Language Detection (pp. 48-52).
  • Mubarak, H., & Darwish, K. (2019, November). Arabic offensive language classification on twitter. In International Conference on Social Informatics (pp. 269-276). Springer, Cham.
  • Elmadany, A., Mubarak, H., & Magdy, W. (2018). Arsas: An arabic speech-act and sentiment corpus of tweets. OSACT, 3, 20.
  • Mubarak, H., Darwish, K., & Magdy, W. (2017, August). Abusive language detection on Arabic social media. In Proceedings of the first workshop on abusive language online (pp. 52-56).
Module URL Body of Request
Dialect ID https://asad.qcri.org/dialect
Sentiment https://asad.qcri.org/sentiment
Emotion https://asad.qcri.org/emotion
News Category https://asad.qcri.org/news_category
Offensive Language https://asad.qcri.org/offensive KEY : text
Hate Speech https://asad.qcri.org/hate VALUE : text_for_classification
Adult Content https://asad.qcri.org/adult
Spam https://asad.qcri.org/spam
Gender https://asad.qcri.org/gender
Location https://asad.qcri.org/location
Name2Country https://asad.qcri.org/name2country

Table: URLs and body of post request to access ASAD modules.

Example of calling ASAD from Python

import requests, json
text = "@USER القوات راكبه امايتكن واحد واحد من كبيركن ل صفيركن . و صرمايه كل فرد و وزير او نائب اشرف من راس بياتكن و يا بجم يا حواش انتم سرطان المجتمع اللبناني ."
url = "https://asad.qcri.org/offensive"
myobj = {'text': text}
x = requests.post(url, data = myobj)
res = json.loads(x.text)
print (res)  
Output is:
{'not_offensive': 28.0, 'offensive': 72.0, 'prediction': 'offensive'}