Publications Data Analytics & CS

Internet Response League (Using Massive Multiplayer Online Games to make sense of "Big Data" during disasters). In collaboration with the United Nations.

Arabic e-book reader - an application that supports right-to-left script and other requirements for the Arabic language

NADEEF (which means ''clean'' in Arabic) is an extensible and generalized data cleaning system.  Released as open source, NADEEF allows users to implement their own data repairing algorithms to replace default NADEEF data repair implementation.  

• Research paper (SIGMOD)
• Dashboard (via Github)

The World Bank's Auto Geotagger is a prototype which automatically identifies locations in documents from the World Bank Projects Data API using the Stanford Name Entity Recognizer (NER) and Alchemy, geocodes them with the Google Geocoder, Yahoo! Placefinder , and Geonames and visualizes them on a map.

Humanitarian UAV Network (UAViators). In collaboration with multiple partners. UAViators promotes Big Data solutions for aerial imagery analysis and facilitates the safe & responsible use of UAVs in a wide range of humanitarian settings. UAViators was recently endorsed by the United Nations.

QATS:  QCRI Advanced Transcription System, a state-of-the-art speech recognition system for Modern Standard Arabic, is now live on Aljazeera.net!  Select daily or archived videos and turn on the closed caption feature.
 

Distributed and Approximate Big Data Analysis: This project aims to enable important machine learning algorithms to efficiently process massive datasets. We achieve this goal using two techniques: controlled approximation and elastic distribution of computation.

More info can be found in our HPDC 2012 paper.

Analytics on Data Anomalies. Oftentimes users face errors in the results of a query. We introduce DBRx, a system for discovering concise explanations of data anomalies. 

Verily (Crowdsourced Verification for Disaster Response). In partnership with the Masdar Institute’s Social Computing and Artificial Intelligence Lab. Using time-critical crowdsourcing to rapidly verify information posted on social media during disasters. Collaborators include humanitarian organizations and high profile international news organizations.