Building state of the art automated sentiment analysis and opinion mining for Arabic (OMA).
| Name | Description | Publication | Downloads | Extra |
|---|---|---|---|---|
| hULMonA (ﺤﻟﻣﻧا): The first Universal Language Model (ULM) in Arabic | hULMonA is the first Arabic universal language model that can be fine-tuned for almost any Arabic text classification task. Language knowledge learnt unsupervisedly from general-domain dataset is transferred to target task to improve overall performance and generalization. | [19] | hULMonA Data & Code | |
| EmoWordNet 1.0: Automatic Expansion of Emotion Lexicon Using English WordNet/td> | EmoWordNet 1.0 expands the existing emotion lexicon, DepecheMood, by leveraging semantic knowledge from English WordNet (EWN). EmoWordNet 1.0 consisting of 67K terms aligned with EWN, almost 1.8 times the size of DepecheMood. | [18] | EmoWordNet 1.0 | |
| ArSEL 1.0: Arabic Sentiment and Emotion Lexicon | ArSEL is the first large scale Arabic Sentiment and Emotion Lexicon. ArSEL is built in a way to augment the publicly available Arabic Sentiment Lexicon, ArSenL, and to generate a large scale lexicon that includes emotion and sentiment labels for almost every lemma in ArSenL. | [17] | ArSEL 1.0 | |
| ArSenTD-Lev (Arabic Sentiment Twitter Dataset for LEVantine dialect) | The Arabic Sentiment Twitter Dataset for LEVantine dialect (ArSenTD-Lev) is a dataset that contains tweets that are annotated for sentiment and other related information. The dataset contains 4,000 tweets that are retrieved from countries in the Levant Region (Jordan, Lebanon, Palestine and Syria). For each tweet, we provide the following information: the country of origin, the topic being discussed, the sentiment label (on a 5-point scale) and how it is expressed (explicit or implicit), and finally, the target of the sentiment in the tweet. Previous and current research emphasized the importance of having this information to provide more accurate and insightful sentiment analysis results. | ArSenTD-Lev | ||
| ArSenL: Large Scale Arabic Sentiment Lexicon | This is the first publicly available large scale Standard Arabic sentiment lexicon (ArSenL). It is a combination of existing resources of ESWN, Arabic WordNet, and the Standard Arabic Morphological Analyzer (SAMA). | [2, 9] | Slides/Video Links | |
| Annotated Arabic corpora for Credibility | This is a credibility annotated Arabic corpus. | [11] | Slides/Video Links | |
| Arabic Word Embeddings Benchmark and Evaluation Tool | This dataset consists of the first Arabic benchmark for evaluating word embeddings. It also consists of an evaluation that can be used to perform various intrinsic evaluations of the embeddings. | [16] | Slides/Video Links | |
| Annotated Arabic corpora for Sentiment | This is an annotated Arabic Sentiment corpus. | Coming Soon | Coming Soon | Slides/Video Links |
| General-purpose Large Scale Arabic Corpus | This is a large scale Arabic corpus used for general purposes. | Coming Soon | Coming Soon | Slides/Video Links |
| No. | Title | Authors | Venue | Download | Citation |
|---|---|---|---|---|---|
| 1 | A Multiresolution Approach to Recommender Systems | Badaro, G., Hajj, H., Haddad, A., El-Hajj, W., & Shaban, K. B. | Proceedings of the 8th Workshop on Social Network Mining and Analysis, ACM | ||
| 2 | A large scale Arabic sentiment lexicon for Arabic opinion mining | Badaro, G., Baly, R., Hajj, H., Habash, N., & El-Hajj, W. | Arabic Natural Language Processing 2014 | ||
| 3 | A novel approach for emotion classification based on fusion of text and speech | Houjeij, A., Hamieh, L., Mehdi, N., & Hajj, H. | Telecommunications (ICT), 2012 19th International Conference | ||
| 4 | A survey of ground-truth in emotion data annotation | Constantine, L., & Hajj, H. | Pervasive Computing and Communications Workshops (PERCOM Workshops), 2012 IEEE International Conference | ||
| 5 | A framework for emotion mining from text in online social networks | Yassine, M., & Hajj, H. | Data Mining Workshops (ICDMW), 2010 IEEE International Conference | ||
| 6 | Machine Reading for Notion-Based Sentiment Mining | Hobeica, R., Hajj, H., & El Hajj, W. | Data Mining Workshops (ICDMW), 2011 IEEE 11th International Conference | ||
| 7 | Sentence-level and document-level sentiment mining for Arabic texts | Farra, N., Challita, E., Assi, R. A., & Hajj, H. | Data Mining Workshops (ICDMW), 2010 IEEE International Conference | ||
| 8 | Annotating Targets of Opinions in Arabic using Crowdsourcing | Farra, N., McKeown, K., & Habash, N. | In Arabic Natural Language Processing Workshop 2015 | MLA: | |
| 9 | A Light Lexicon-based Mobile Application for Sentiment Mining of Arabic Tweets. | Badaro, G., Baly, R., Akel, R., Fayad, L., Khairallah, J., Hajj, H., … & Shaban, K. B. | In Arabic Natural Language Processing Workshop 2015 | ||
| 10 | Deep Learning Models for Sentiment Analysis in Arabic | Al Sallab, A. A., Baly, R., Badaro, G., Hajj, H., El Hajj, W., & Shaban, K. B. | In Arabic Natural Language Processing Workshop 2015 | ||
| 11 | Arabic Corpora for Credibility Analysis | Ayman AL Zaatari, Rim El Ballouli, Shady Elbassuoni, Wassim El-Hajj, Hazem Hajj, Khaled Shaban, Nizar Habash, Emad Yehya. | Language Resources and Evaluation Conference 2016, 23-28 May 2016, Portorož (Slovenia) | ||
| 12 | A meta-framework for modeling the human reading process in sentiment analysis | R. Baly, R. Hobeica, H. Hajj, W. El-Hajj, K. B. Shaban, and A. Al-Sallab | ACM Transactions on Information Systems (TOIS), 2016 | ||
| 13 | A characterization study of arabic twitter data with a benchmarking for state-of-the-art opinion mining models | R. Baly, G. Badaro, G. El-Khoury, R. Moukalled, R. Aoun, H. Hajj, W. El-Hajj, N. Habash, and K. B. Shaban | WANLP 2017 (co-located with EACL 2017) | ||
| 14 | A Sentiment Treebank and Morphologically Enriched Recursive Deep Models for Effective Sentiment Analysis in Arabic | R. Baly, H. Hajj, N. Habash, W. El-Hajj, and K. B. Shaban, | ACM Transactions on Asian and Low-Resource Language Information Processing (TALLIP), 2017. | ||
| 15 | AROMA: A Recursive Deep Learning Model for Opinion Mining in Arabic as a Low Resource Language | A. Al-Sallab, R. Baly, H. Hajj, K. B. Shaban, W. El-Hajj, and G. Badaro | ACM Transactions on Asian and Low-Resource Language Information Processing (TALLIP), 2017 | ||
| 16 | Methodical Evaluation of Arabic Word Embeddings | Elrazzaz, M., Elbassuoni, S., Shaban, K., & Helwe, C. (2017) | Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 2: Short Papers) | ||
| 17 | ArSEL: A Large Scale Arabic Sentiment and Emotion Lexicon | Badaro, Gilbert, Jundi, Hussein, Hajj, Hazem, El-Hajj, Wassim & Habash, Nizar | OSACT 2018 co-located with LREC | ||
| 18 | EmoWordNet: Automatic Expansion of Emotion Lexicon Using English WordNet | Badaro, Gilbert, Jundi, Hussein, Hajj, Hazem, & El-Hajj, Wassim | Proceedings of the 7th Joint Conference on Lexical and Computational Semantics (*SEM2018) co-located with NAACL-HLT 2018 | ||
| 19 | hULMonA ( ﺤﻟﻣﻧا): The Universal Language Model in Arabic | ElJundi, Obeida, Antoun, Wissam, El Droubi, Nour, Hajj, Hazem, El-Hajj, Wassim, & Shaban, Khaled | Proceedings of the Fourth Arabic Natural Language Processing Workshop (WANLP 2019), Florence, Italy, August 1, 2019. |
 |
Name | Role | Title/Affiliation | Contact Info |
|---|---|---|---|---|
 |
Dr. Hazem El Hajj | Lead Principal Investigator | Associate Professor, Electrical and Computer Engineering, American University of Beirut | |
 |
Dr. Khaled Bashir Shaaban | Co-lead Principal Investigator | Associate Professor, Computer Science and Engineering Department, Qatar University | |
 |
Dr. Wassim El Hajj | Principal Investigator | Associate Professor and Chairman of Computer Science, American University of Beirut | |
 |
Dr. Nizar Habash | Principal Investigator | Associate Professor of Computer Science, New York University Abu Dhabi (NYUAD) | |
 |
Dr. Shady Elbassuoni | Collaborator | Assistant Professor of Computer Science at the American University of Beirut | |
 |
Dr. Kathy McKeown | Collaborator | Henry and Gertrude Rothschild Professor of Computer Science. Director, Data Science Institute |
|
Name | Role | Title/Affiliation | Contact Info |
|---|---|---|---|---|
 |
Ramy Baly | Research Assistant | PhD Candidate in the Electrical and Computer Engineering Department, American University of Beirut | |
 |
Gilbert Badaro | Research Assistant | PhD Candidate in Electrical and Computer Engineering at the American University of Beirut | |
 |
Ayman Al Zaatari | Research Assistant | Graduate Student and Assistant Instructor of Computer Science, American University of Beirut | |
 |
Reem El Ballouli | Research Assistant | MS student in the Computer Science department, American University of Beirut | |
 |
Wafa Waheeda Syed | Research Assistant | Graduate Student, Computer Science and Engineering Department, Qatar University | |
 |
Noura Farra | Research Assistant | PhD student in Computer Science at Columbia University | |
| Obeida ElJundi | Research Assistant | MS student in the Electrical and Computer Engineering Department, American University of Beirut | ||
| Wissam Antoun | Research Assistant | MS student in the Electrical and Computer Engineering Department, American University of Beirut | ||
| Nour El Droubi | Research Assistant | MS student in the Electrical and Computer Engineering Department, American University of Beirut |
This work was made possible by NPRP 6-716-1-138 grant from the Qatar National Research Fund (a member of Qatar Foundation). The statements made herein are solely the responsibility of the authors.
