“The Artificial Intelligence for Digital Response (AIDR) has recently been deployed in conjunction with Unicef in Zambia to classify short messages received through its U-Report platform. AIDR aims to enable Unicef make sense of a large volume of short messages in a timely manner,’ Dr Mohamed Imran, a scientist with QCRI told Gulf Times.
U-Report is Unicef’s groundbreaking, text-message based innovation that amplifies the voices and views of young people in developing countries, on various health related issues.
QCRI has made extensive use of AIDR in several areas including health and disaster management. It is a free and open platform to filter and classify social media messages related to emergencies, disasters, and humanitarian crises. AIDR uses human and machine intelligence to automatically tag up to thousands of messages per minute.
“In response to the growing HIV/AIDS and other health related issues, Unicef receives thousands of SMS messages every day to provide prevention strategies, health case advice, and counselling support to vulnerable population. However, it is very difficult for some 10 to 15 counsellors at the headquarters of the organisation to analyse and answer all these questions and this is where the technology comes in handy,” explained the scientist.
“QCRI introduced this technology to help answer the questions and classify the messages.The platform can classify these questions into categories and then can answer these questions. However, it can answer only those questions that have already been discussed. For a given question, we try to give the best answer as well as the best solutions,” he continued.
“QCRI employs a hybrid approach, which combines human and machine intelligence that seeks to resolve the information overload issue by introducing processing of large-scale data at high-speed while maintaining a high classification accuracy. In terms of evaluation, we report design choices, challenges, and performance of the system observed during the deployment to validate its effectiveness,” highlighted the scientist.
Dr Imran pointed out that the technology was deployed during the outbreak of Mers and Zika virus so that people could get proper guidance. The open ended platform also listens to social media such as Twitter and Facebook and answers questions.
The official said that QCRI was keen to have this technology deployed in as many areas as possible.“We are looking forward to having this technology deployed in many other countries.We have already signed agreements with several organisations such as UNOCHA, Unicef and several other organisations,” he noted.
“AIDR was deployed effectively in most of the natural disasters such as earthquakes and cyclones that took place in the recent years. We have been able to filter through thousands of messages and provide effective tips on a timely manner at such occasions,” added Imran.
![AIDR uses human and machine intelligence to automatically tag up to thousands of messages per minute. AIDR uses human and machine intelligence to automatically tag up to thousands of messages per minute.](https://www.gulf-times.com/uploads/imported_images/Upload/Slider/1220161620420929879232.jpg)
AIDR uses human and machine intelligence to automatically tag up to thousands of messages per minute.
A digital platform, developed by Qatar Computing Research Institute (QCRI), a research institute under Hamad Bin Khalifa University, has been deployed in various countries to tackle several health related issues as well as humanitarian crises, a senior official disclosed.