Header Information

NPRP 6 - 1377 - 1 - 257
NPRP 06
Qatar University
Award Closed
10 Feb 2014
Dr. Tamer Elsayed
3 Year(s)
31 May 2017
New
Answering Real-time Questions from Arabic Social Media

Project Summary
Systems designed to help users answer questions have traditionally focused on analyzing formal content (e.g., full web pages and news articles) to find answers (or nuggets) to asked free-text questions. However, little attention has been given in building those systems to analyzing online informal content (such as millions of posts and tweets that are created daily on Facebook and Twitter). The rapid increase of popularity and interest in that type of media, especially in the Arab world, as both conversational and information dissemination channels, makes it a potential rich source of answers to real-time questions. In this proposal, we plan to address the problem of answering users’ questions from Arabic content in social media. While the type of data allows new user-centric questions to be asked (e.g., what are the different opinions on a decision made by a national figure right after it was made), it also opens up new challenges, such as dealing with different dialects, mixed languages, and conversational content, in addition to the unique characteristics of the Arabic language. We propose to explore the solution space from several different perspectives, e.g., ranked retrieval, topic modeling, and information visualization. In solving the problem, we plan to build a scalable open-source real-time system that answers given questions while providing plausible explanations of selecting the presented answers.
By far the most important outcome of this project will be the potential establishment of Qatar as a global hub for research on emerging problems in system support for information access. This objective will be achieved in three ways: (1) fostering the emergence of a world-class academic research team at QU, with the close collaboration with top researchers in the field and the expansion in human capacity and necessary research infrastructure (2) full alignment with important research priorities of both QNRS and QCRI, and (3) experience with drawing upon unique assets in Qatar, most notably Al Jazeera, but also faculty with related interests in other Qatari universities. QCRI has expressed their support and interest in collaboration on parts of this work (check attached support letter from their side) and we are planning to assist with ongoing integration of our code in their continuing work, even after completion of the project. We will also encourage further development of this potential by organizing a workshop at Qatar University in the third year of the project (using other funds) in which we will bring together these stakeholders, our international partners in this project, and a few selected invited participants. This workshop will help in gaining more academic reputation in the international information retrieval community for QU and Qatar.
Social media; Real-time; Question Answering; Arabic; Scalable service
Applied research
1. Natural Sciences
1.2 Computer and Information Sciences
Computer Sciences
Yes
No

Institution
Qatar University
Qatar
Submitting Institution
University of Maryland, College Park
United States
Collaborative Institution
Royal Melbourne Institute of Technology University (RMIT)
Australia
Collaborative Institution

Personnel
Lead PI
Dr. Tamer Elsayed
Qatar University
Co-Lead PI
Dr. Tamer Elsayed
Qatar University
PI
Prof. Mark Sanderson
Royal Melbourne Institute of Technology University (RMIT)
PI
Prof. Douglas Oard
University of Maryland, College Park

Outputs/Outcomes
Conference Paper
Query Performance Prediction for Microblog Search: A Preliminary Study
Maram Hasanain, Rana Malhas, Tamer Elsayed
DOI:10.1145/2632188.2632210
Conference Paper
Identification of Answer-Seeking Questions in Arabic Microblogs
Maram Hasanain, Tamer Elsayed, Walid Magdy
DOI:10.1145/2661829.2661959
Conference Paper
QU at TREC-2014: Online Clustering with Temporal and Topical Expansion for Tweet Timeline Generation
Maram Hasanain and Tamer Elsayed
DOI:10.08/2014-trec-microblog
Conference Paper
Improving Tweet Timeline Generation by Predicting Optimal Retrieval Depth
Maram Hasanain, Tamer Elsayed, and Walid Magdy
DOI:10.1007/978-3-319-28940-3-11
Conference Paper
Profession-Based Person Search in Microblogs
Mossaab Bagdouri, Douglas W. Oard
DOI:10.1145/2806416.2806466
Conference Paper
On Predicting Deletions of Microblog Posts
Mossaab Bagdouri and Douglas W. Oard
DOI:10.1145/2806416.2806600
Journal Paper
Unsupervised adaptive microblog filtering for broad dynamic topics
Walid Magdy and Tamer Elsayed
ISSN:03064573
Conference Paper
Cross-Platform Question Routing for Better Question Answering
Mossaab Bagdouri
DOI:10.1145/2766462.2767849
Conference Paper
EveTAR: A New Test Collection for Event Detection in Arabic Tweets
Hind Almerekhi, Maram Hasanain, Tamer Elsayed
DOI:10.1145/2911451.2914681
Conference Paper
Pearson Rank
Ning Gao, Mossaab Bagdouri, and Douglas W. Oard
DOI:10.1145/2911451.2914728
Conference Paper
What Questions Do Journalists Ask on Twitter?
Maram Hasanain, Mossaab Bagdouri, Tamer Elsayed, Douglas Oard
DOI:10.2016/13221
Conference Paper
On the Evaluation of Tweet Timeline Generation Task
Walid Magdy, Maram Hasanain, Tamer Elsayed
DOI:10.2016/ecir.648
Conference Paper
QU-IR at SemEval 2016 Task 3: Learning to Rank on Arabic Community Question Answering Forums with Word Embedding
Rana Malhas, Marwan Torki, Tamer Elsayed
DOI:10.2016/semeval.866
Conference Paper
On the Evaluation of Tweet Timeline Generation Task
Walid Magdy, Maram Hasanain, Tamer Elsayed
DOI:10.1007/978-3-319-30671-1-48
Conference Paper
QU at TREC-2015: Building Real-Time Systems for Tweet Filtering and Question Answering
Reem Suwaileh, Maram Hasanain, Marwan Torki, Tamer Elsayed
DOI:10.2016/trec.qu
Conference Paper
CLIP at TREC 2015: Microblog and LiveQA
Mossaab Bagdouri, Douglas W. Oard
DOI:10.2016/trec.umd
Conference Paper
Language Influences on Tweeter Geolocation
Ahmed Mourad, Falk Scholer, Mark Sanderson
DOI:10.1007/978-3-319-56608-5
Conference Paper
CLIP at TREC 2016: LiveQA and RTS
Mossaab Bagdouri and Douglas W. Oard
DOI:10.2017/trec.umd
Conference Paper
Building Bridges across Social Platforms: Answering Twitter Questions with Yahoo! Answers
Mossaab Bagdouri and Douglas W. Oard
DOI:10.1145/3077136.3080755
Conference Paper
QU-BIGIR at SemEval 2017 Task 3: Using Similarity Features for Arabic Community Question Answering Forums
Marwan Torki and Maram Hasanain and Tamer Elsayed
DOI:10.2017/semeval.360
Conference Paper
Real, Live, and Concise: Answering Open-Domain Questions with Word Embedding and Summarization
Rana Malhas, Marwan Torki, Rahma Ali, Evi Yulianti, Tamer Elsayed
DOI:10.2017/trec.liveqa.qu
Conference Paper
Light-weight, Conservative, yet Effective: Scalable Real-time Tweet Summarization
Reem Suwaileh, Maram Hasanain, Tamer Elsayed
DOI:10.2017/trec.rts.qu
Conference Paper
QweetFinder: Real-Time Finding and Filtering of Question Tweets
Ameer Albahem, Maram Hasanain, Marwan Torki, and Tamer Elsayed
DOI:10.1007/978-3-319-56608-5 79
Conference Paper
Language Influences on Tweeter Geolocation
Ahmed Mourad, Falk Scholer, and Mark Sanderson
DOI:10.1007/978-3-319-56608-5 26
Online Paper
Journalists' information needs, seeking behavior, and its determinants on social media
Omid Aghili, Mark Sanderson
DOI:10.2017/arXiv.1705.08598v2