Ibrahim Abu Farha


I am a PhD student at the School of Informatics, the University of Edinburgh. I am working under the supervision of Walid Magdy and Bonnie Webber. I am also a member of the SMASH research group. My general research interests are Natural Language Processing (NLP), Arabic NLP, Computational Social Science and Machine Learning. My current research interest is sarcasm detection and figurative language anlaysis and detection in the context of Arabic.
In 2018, I completed my MSc in Artificial Intelligence at the University of Edinburgh. During my masters I focused on machine learning and NLP. My dissertation was about Arabic sentiment analysis, where I focused on utilising and comparing deep learning models for that task. Finally, I Completed my BA in Computer Systems Engineering from Birzeit University in Palestine. My final year graduation project was about Automatic Arabic Text Summarization.


Publications

  • Abu Farha I. and W. Magdy. "A Comparative Study of Effective Approaches for Arabic Sentiment Analysis". Information Processing & Management (IP&M) Journal 2021 link

  • Abu Farha I., W. Zaghouani and W. Magdy. "Overview of the WANLP 2021 Shared Task on Sarcasm and Sentiment Detection in Arabic". WANLP - EACL 2021 to appear

  • Abu Farha I. and W. Magdy. "Benchmarking Transformer-based Language Models for Arabic Sentiment and Sarcasm Detection". WANLP - EACL 2021 to appear

  • Abu Farha I. and W. Magdy. "From Arabic Sentiment Analysis to Sarcasm Detection: The ArSarcasm Dataset". OSACT4 - LREC 2020 link

  • Abu Farha I. and W. Magdy. "Multitask Learning for Arabic Offensive Language and Hate-Speech Detection". OSACT4 - LREC 2020 link

  • Abu Farha I. and W. Magdy. "Mazajak: An Online Arabic Sentiment Analyser". WANLP - ACL 2019 link, live demo

  • Qaroush A., I. Abu Farha, W. Ghanem, M. Washaha, and E. Maali. "An efficient single document Arabic text summarization using a combination of statistical and semantic features". Journal of King Saud University – Computer and Information Sciences 2019. link


Resources

ArSarcasm Dataset (v2)

  • An extension of the original ArSarcasm. It contains around 15K tweets labelled for sarcasm, sentiment and dialect.

  • The standard dataset for the shared task on sarcasm and sentiment detection in Arabic . We recommend using ArSarcasm-v2 over ArSarcasm-v1.

  • Available here

  • Abu Farha I., W. Zaghouani and W. Magdy. "Overview of the WANLP 2021 Shared Task on Sarcasm and Sentiment Detection in Arabic". WANLP - EACL 2021 to appear

ArSarcasm Dataset (v1)

  • A set of around 10K tweets labelled for sarcasm, sentiment and dialect.

  • Available here

  • Abu Farha I. and W. Magdy. "From Arabic Sentiment Analysis to Sarcasm Detection: The ArSarcasm Dataset". OSACT4 - LREC 2020 link

Mazajak Arabic Sentiment Analyser

  • Free online Arabic Sentiment Analysis tool and API

  • Available here

  • Related publication:
    Abu Farha I. and W. Magdy. "Mazajak: An Online Arabic Sentiment Analyser". WANLP - ACL 2019 link

Mazajak Arabic Word Embeddigs

  • Arabic Word Embedding set for social media.

  • Word2vec vectors built using CBOW and Skip-gram Architectures.

  • Built using 250M tweets.

  • Available for free here

  • Related publication:
    Abu Farha I. and W. Magdy. "Mazajak: An Online Arabic Sentiment Analyser". WANLP - ACL 2019 link


Experience

Research Assistant

The University of Edinburgh

Main Researcher on Mazajak project for Arabic sentiment analysis.

August 2018 - January 2019

Teaching and Research Assistant

Birzeit University

As a Teaching and Research Assistant at the Electrical and Computer Engineering department, I was responsible of tutoring various specialized labs such as Computer Networks, Microprocessers, Linux, and Real Time Systems.

March 2016 - August 2017

.NET Intern

iConnect Technologies

Internship and practical training on using .NET framework.

June 2015 - August 2015

Contact

Email: i.abufarha@ed.ac.uk

Informatics Forum
University of Edinbrugh
10 Crichton Street
Edinburgh
United Kingdom
EH8 9AB