Invited Speaker

Invited Speaker

Dr. Walid Magdy

Bio: Walid Magdy is an Assistant Professor at the School of Informatics, the University of Edinburgh (UoE), UK. His main research interests include computational social science, information retrieval, and data mining. He holds his PhD from the School of Computing at Dublin City University (DCU), Ireland. He has an extensive industrial background from working earlier for IBM, Microsoft, and QCRI. Walid has over 60 peer-reviewed published articles in top tier conferences and journals. He also has a set of 9 patents filed under his name. Some of his work was featured in popular press, such as CNN, BBC, Washington Post, National Geographic, and MIT Tech reviews.

* * *

Personal web page:  http://homepages.inf.ed.ac.uk/wmagdy/

* * *

Title: Beyond Developing Basic Arabic NLP Tools, the Era of Social Media Analysis

* * *

Date: November 17th, 2018 10:00 AM
Location: Auditorium
Conference Venus: The British University in Dubai

* * *

Abstract: Research in Arabic NLP has been growing over the last two decades, leading to the development of language technologies tools for Arabic. The main focus has been for a long time on modern standard Arabic (MSA), which led to tools achieving high accuracies for basic NLP tasks, such as stemming, POS tagging, and named-entity recognition. With the recent spread of social media, a new field has emerged which is computational social science, where the objective is to study social science phenomena using computational methods by analysing big social data. This required some additional NLP tools for Arabic dialects, such as sentiment analysis, sarcasm detection, speech-act recognition, and others. In this talk, we show few examples of computational social science studies on Arabic social media, such as understanding antecedent of ISIS support on social media, Network dynamics during Egyptian military intervention in 2013, and the share of Quran on social media. In addition, we show the progress work on some of the tools for Arabic dialects analysis, such as POS for dialect, sentiment analysis, and speech-act recognition. We also highlight the gabs in these tools to motivate future directions.

* * *