UNICEF, IBM support Africa
The U.S. fund for UNICEF in collaboration with UNICEF–Uganda has announced a free SMS-base reporting tool that allows Ugandan youth to communicate with their government and community leaders using their cell phones.
The programme, which was launched in 2011, began as bases for text-messaging and help conduct weekly polls on opinions, observations and issues affecting their lives.
A press release signed by Charles Moyela, IBM External Relations leader in West Africa said as a result of the ‘U-report’ there has been an increase in text-messaging and the volume of diverse data is becoming a challenge for the existing system, making it impossible to determine the existing and recent messages.
It said the IBM research and UNICEF Uganda has deployed A-class, a text classification system which trained the youth to understand the content of the text-messages and analyse data faster and accurately.
The statement also said the IBM Analytics in combination with UNICEF Uganda, had made it possible for other organisational bodies like UNICEF, partners and community leaders in using the existing classification process to make more informed decisions about a place, how to prioritize, develop and to make work comfortable for them.
“This project has the potential to change the lives of young people in Uganda simply by giving them the platform to communicate and be heard” it stated.
Also, it stated that technology has helped in understanding the real impact of policies and development programmes in the country.
“We are working towards removing the speculative work out, in order to know where to put resources in areas where they are needed”, it stated
It said the collaboration has been a powerful demonstration, and that, the text-analytics logarithms developed by IBM Research have made the U-report smarter and innovative for UNICEF to be accurate in identifying matters among the youth in Uganda.
The A-Class text classification model was developed by IBM Research, using a combination of supervised machine learning, the latest advances in text mining and keyword matching.
The objective of the model is to classify each incoming text message into one of 12 UNICEF message categories – this classification task has particularly challenged the brevity and frequent misspellings in SMS messages.
Based on the success of the U-report program in Uganda, UNICEF has launched it in Zambia, Burundi and South Sudan, with a roll out expected in the Democratic Republic of Congo.
The technology in collaboration with IBM will also continue to explore how to automatically assign action status to messages, making the system portable in other countries and understanding how the system could be implemented in non-English environments.
U-report relies on RapidSMS, an open source software framework that works with any cell phone on the market, enabling UNICEF to connect with communities, using a low-cost and popular device.
Results from U-report surveys are publicized via the Polls Results section of the websites, and messages classified by A-Class are captured in real-time and displayed on the National Pulse page, allowing the public to visualize what issues are trending within each district in Uganda.
Reports are also shared within government officials via newsletters and national media channels to ensure decision makers have access to information regarding their districts.
This initiative is supportive of IBM’s mobile computing vision, Mobile First, which is rooted in the notion that innovative organizations connect with mobile users, build insights through more powerful analytics, deliver more convenient and relevant engagements, and improve management and customer service with seamless integration of front-end functionality and back-end data.
Source: GNA