Daily Archives: 26 October 2012

Automated Texting Services for Low-Resource Languages

Following our class period with Robert Munro, I found myself browsing through his Twitter and found an article describing his PhD topic in an August 9th Tweet. Within the article, he elaborates on some of the concepts discussed in class; as he explains, so many of the 5,000+ languages of the world are being written for the first time ever with the proliferation of mobile telephony, but the technology to process these languages cannot keep up. Compounding the problem, these phone users are of varied literacy levels, making for spelling inconsistencies among users. However, he concludes that automated information systems can pull out words that are least likely to vary in spelling (ie people, places, organizations) and examine subword variation by identifying affixes within words as well as accounting for phonological or orthographic variation (ie recognize vs. recognise). The article goes on to provide more technical prescriptions for automated text response services, and he even links to another article in a separate Tweet, which describes Powerset, a natural language search system that ultimately failed, but utilized a few valuable processes.

Ultimately, Dr. Munro implies that the capacity for automated text services in “low-resource languages” is well within reach, particularly because the messages are generally just one to two sentences. Because spelling variations are predictable, they can be modeled, and hopefully reliably answered by automated systems. However, the use of these systems will not be realized until they become more reliable and efficient than human responders, which, as he explained in class, can be extremely effective.

Advertisements

Mobile Banking in Africa

Mobile Banking in Africa

In class, we have discussed a phenomena that is common in development called ” The Leapfrogging Effect.”  The Leapfrogging Effect, when discussed with ICT4D, is what happens when a developing country skips over an entire generation of a specific type of technology, and jumps straight into a very new, modern kind.  For example, in Africa, there is often a prevalance of mobile phone users, however, landlines are often very rare.  This is attributed to the leapfrogging effect, and that once the countries in Africa had the means to implement the phone technologies, it did not make sense for them to waste their money installing infrastricutre for their outdated landline phones, but rather jumped straight ahead to invest in mobile phone technology, leading a large portion of people in Africa to have never had a landline, but to have cell phones now.

This article by The Economist does not directly discuss the leapfrogging effect, but indirectly proves it.  It discusses how African nations are often way ahead of developed countries in the use of mobile banking.  Although not explicitly stated, one hypothesis for this is that possibly the rise of large and modern banks in African countries never developed as they did in the developed world.  However, now as they begin to get their foot in the door of banking, they will leapfrog ahead straight to mobile banking, rather than invest their money in a more archaic type of banking.


Mapping Malaria in Africa

This article describes an innovative approach to using ICT for development initiatives. Malaria remains one of the deadliest diseases on the planet with a great deal of malaria cases occurring in sub-Saharan Africa.In order to track and prevent the disease, it is necessary to know where people live. Though this sounds simple, it is harder than one might think in Africa. A new project, the AfriPop Project, used cell phone records in Kenya to track popular travel routes between population centers, therefore mapping the location of almost 15 million people. The project then applied this map to a malaria transmission model to reveal how malaria is likely to spread in Kenya. The use of cell-phones, rather than GPS, surveys, and traffic flow data, provided exponentially more data, making the transmission model much more effective and powerful. This technique maximized very limited resources in order to help prevent the transmission of malaria in Kenya.

How could this technique be replicated in other countries? In what fields, other than disease transmission, might it be applicable? What are potential drawbacks of this approach?


Crowdsourcing ICTs and Education

The World Bank has recently recognized the value in crowdsourcing for development. Last year the World Bank Disaster Management used crowdsourcing in Latin America and the Caribbean, partnering with Yahoo, Google, and NASA, among others. Recently they have applied crowdsourcing to the educational field, in response to systemic problems at the local and regional levels. Crowdsourcing could be used to raise low scores by sending out requests for instructional success stories, or to connect teachers to share educational strategies and solutions. One program that has already been implemented is the Open Innovation Portal, started by the US Department of Education. Open Innovation uses crowdsourcing to bring teachers together to share their knowledge on problems plaguing school systems such as dropout rates and difficult children. The program has seen instant results. Just four months after the start of the program, over 4,000 people signed up and shared many innovative ideas that may receive donor funds in order to be more successfully implemented or merely used as effective methods by other participants in the program. This is just one example of crowdsourcing being used here in the U.S. to promote educational solutions. This demonstrates one of the nearly endless ways that crowdsourcing may be utilized as it becomes a more popular strategy in ICT4D.


FrontlineSMS: The Impact of Open Source Tools for Development

Through Mission 4636, 80,000 earthquake victims throughout Haiti were able to solicit help via text message. What’s most astonishing about the project is not the large number of people it was able to help, but the speed at which it was set into motion. From conception to launch, the Mission 4636 came together in a mere 48 hours. People from 10 organizations from around the world dropped everything to build the best platform possible. Among these organizations was one that caught my eye, Frontline SMS:medic, whose director was responsible for obtaining the short code “4636” for the project.

Frontline SMS:medic is one of many programs that utilizes the FrontlineSMS free software program. Through FrontlineSMS, users can text large groups of people anywhere there is a mobile signal. FrontlineSMS enables instantaneous, two-way communication on a large scale by utilizing computers and mobile phones—two technologies that are available to most NGOs. This means a laptop plugged into a cell phone can become a low-cost communication hub. Frontline SMS makes use of open-source software to support development services across the globe and provides easily implemented solutions to many communication barriers in developing countries.

FrontlineSMS:medic is one of the most successful initiatives of the 5 FrontlineSMS programs (others are credit, learn, legal, and radio).  It utilizes FrontlineSMS to improve and extend healthcare delivery systems by helping health workers communicate, coordinate patient care, and provide diagnostics using appropriate cost-effective technologies. The pilot program was launched in 2009 to great results: in six months, hospital workers saved 1200 hours of follow up time and an accompanying $3000 in motorbike fuel. In less than one year, FrontlineSMS:Medic grew to 1,500 end users who were serviced by clinics seeing approximately 3.5 million other patients. Growing from the first pilot at a single hospital in Malawi, programs were subsequently established in 40% of Malawi’s district hospitals and the software was introduced in nine other countries, including Honduras, Haiti, Uganda, Mali, Kenya, South Africa, Cameroon, India and Bangladesh.

FrontlineSMS demonstrates the importance of building upon and implementing open source tools to serve end users and achieve impact in the field of development. For complete information on FrontlineSMS click here. For complete information on FrontlineSMS:Medic click here.


Mobile Banking: A Brief Overview

ImageOne of the most promising technological tools in the developing world is the mobile phone. Although there is still a significant difference in levels of mobile phone access and mobile phone usage, banking and money transfer has emerged as an area in which mobile phone technology can be useful and effective. This article gives a brief overview of the extent to which mobile banking has become a widely used technology. While in Eurpoe and North America, online banking is the norm, mobile banking is gaining more and more users in Asia, Africa, the Middle East and Latin America, where people do not have as easy access to computers. While we generally talk about developing countries benefitting from The Leapfrog Effect, it seems like in this case, developing countries have leaped right over online banking and found a solution more fitting to their needs. According to a Swedish industry research firm, mobile banking is expected to reach 894 million users by 2015. That would be a sixteenfold increase from 55 million users in 2009. Many companies in the developing world are looking to be the first to invest in mobile banking technology, and this field could perhaps become a booming global industry.


Using Cell Phones to Combat Poverty

New research has found that social media and access to ICT is a confirmed pathway out of poverty. This finding is huge in the ICT world because it proves that merely a mobile phone can lead to an increase in income. This kind of result is something that academics, government officials, and NGOs have been looking for to confirm a way to overcome poverty and inequality. This study occurred during 2008 and 2010 where, during dramatic food price increases and economic crisis, “the income of the poorest people who had access to mobile phones went up.”

An African woman using a mobile phone in her village.

Adding education and entrepreneurship skills, another finding suggests, increases income even further. How? Well, mobile phones can be used to grow income with communication networks, checking on food prices, job offers, or even finding ways to send money to relatives. Farmers in Uganda and Rwanda can send SMS messages to a free number to hear what coffee prices are in local markets. M-Pesa, the East Africa mobile-based service that we studied in class, was discussed as a hugely successful initiative that enabled 17 million people to deposit, withdraw, and transfer money.

What experts are looking to do is to “create platforms that bypass traditional barriers of cost and accessibility and equip youth with the skills and information they need to seek out opportunities.” The mobile technology can become a bridge to many different connections. Like the case studies that we looked at in class regarding India, Kenya, and Afghanistan, given the chance, mobile phones can make a huge difference.