Short Message Service (SMS) text messages, which started as a way for Nokia engineers to test mobile phone network operations, has grown into a killer app - for everyone. At the SMS4Dev Technology Salon in San Francisco, we looked at three ways to apply SMS to pressing development projects.

SMS:Gov

First we discussed the issue of local government communications with their constituencies. The problem being that usually they don't communicate with constituencies outside of infrequent in-person meetings.

By employing software like FrontlineSMS in a SMS:Gov usage model, local governments could offer two compelling services: 311 and MyObama.

• 311: By offering a single, simple text message menu tree using keywords, local governments can categorize constituent needs and wants into categories for prompt response, like the 311 systems in New York, Washington DC, and San Francisco.
• MyObama:Local politicians can use the same process to become knowledgeable on the electorate's concerns, and individualize their message to respond to those concerns, like MyObama did to great success in 2008

Rob Munro discussing his SMS efforts

Categorizing SMS via Artificial Intelligence

But what if the categories for keywords are not known in advance, or a community doesn't understand the concept of a keyword? Rob Munro faced this challenge in Malawi when implementing FrontlineSMS with rural Community Health Workers (CHWs) who mainly use the Chichewa language.

The doctors at a central clinic spend one hour each day managing incoming CHW text messages, but with a patient population of 250,000 this averages to just 5 seconds per patient per year, and so any automation for triage incoming text messages from CHWs can lead to huge productivity increases.

Rob developed self-learning artificial intelligence algorithms that parsed free form SMS text messages in three different ways:

1. Normalizing spelling variants of keywords by learning linguistically predictable alternations
2. Segmenting words into their component morphemes to identify key substructures (like "patient" as the key form of "patients")
3. Using the normalized/segmented data to classify each message to determine its urgency - patient-related vs. administrative texts

With the algorithm learning from just 600 text messages it was was able to achieve about 95% accuracy, which should hold across any language using an alphabetic writing system and improve as the volume of text messages increases.

Applying SMS to Private Industry

Stepping away from SMS itself, Zach Berke spoke about two ways in which his company, Exygy, is developing text messages to support private industry expansion into the developing world.

• Payment plans: Solar power can be expensive, but how do you have a payment plan for an installed system? Require owners to text in codes they buy from local retailers to unlock another set amount of usage.
• Pharmaceutical validity: Counterfeit pills are a huge issue for consumers, but a simple code printed on a package can be texted to a central verification system to confirm drug authenticy.

Now both of these systems have their challenges. For the solar system, how do you pre-set codes into the hardware, or keep someone from soldering around the payment device. For pharmaceuticals, its printing variable yet secret codes on a specific end-user level package, with each code unique yet short enough to text without error.

Yet it can be done. Unicef used RapidSMS to track the distribution of 63 million mosquito bed nets across Nigeria with test messages on ordinary mobile phones using no-charge SMS shortcodes.

Where the last SMS4D Technology Salon reminded us of the unique gift of mobile technologies to be implemented in the field, The Cloudy SMS4D Salon really drove home mobile phones as a multifunctional tool whose true impact is tied more to the usage than the technology itself.

While we gathered to discuss SMS4D, we really talked about heath reporting and outreach, education, and community building through knowledge management and sharing. It just so happened that these health projects were using SMS codes to report longitudinal child health statistics.

Data gathering in health, and even knowing when to gather data, is a huge burden, often relying on community health workers doing the healthcare version of the Training and Visit system of the agricultural extension world. Waiting around for a planned infrastructure is hopeless, but working with the more incremental nature of mobile can improve reporting rates and reduce errors -- "utter chaos works everywhere" being the best quote of this Technology Salon.

ChildCount+

Childcount builds on existing SMS reporting to enable community health workers to rapidly register children, note any symptoms or diseases they might have, improve patient tracking (and thereby reducing duplication), and schedule immunizations and outreach. The SMS "encoding" builds off of a simple and familiar paper form, which is handy for training (but less useful than a mango tree, as we'll see).

The runner-up quote from this Salon dealt with discussion around the potential risk of intentionally fabricated data -- "humans are awful at falsifying data" -- digitizing and quick, auditable reporting exposes both errors and lies.

Happy Pill

Winning the award for innovative ideas in mHealth was the HappyPill project -- instead of boring old SMS, HappyPills uses "flashing" - where you call a number and hang up immediately to "ping" someone. Usually, flashing is just a free way to ask someone to call you back, or you can sometimes work out extensive codes -- one missed call is just saying hi, two is call me back, three means an emergency, etc..

HappyPills takes this basic, essentially binary interaction and applies it to help improve adherence rates for prescription regimens. A medical center can send out flashes to their patients, and the patients are reminded to take their pills and would then flash back to signal that they took their medicine. It's naturally not foolproof, but hugely more cost effective (almost cost-free) in comparison with sending a community health worker out to the patient on a motorcycle to witness their pill-taking.

Jokko Initiative

It turns out that people are not just willing, but economically motivated and excited to use (and pay for) basic SMS-based services to improve their numeracy and literacy skills, improving their ability to communicate cheaply over their phones as well as better navigate market prices. In these low-technology communities, Tostan's Jokko Initiative is creating a curriculum to enable this via SMS.

Mango tree mobile phone menu navigation

They have also come up with an amazingly simple methodology to introduce people to menu systems using a mango tree metaphor which gracefully transitions from the concrete (planning a climbing route on a real tree to get to a specific mango) to the semi-concrete (the same, on a diagram of a tree), to the abstract (the tree diagram becomes the menu diagram, the mango a specific function).

Anyone who thinks that is too basic has never shown their grandparents a new shiny piece of technology, or had their entire worldview of user interface challenged by someone physically pointing a mouse at a screen).

Patatat

Patatat is an early-stage solution, which puts SMS into the role of a community town hall, newsletter, or email list. It removes not only the normal geographic barriers that a listserv gets around, but also infrastructure barriers, so (for example) farmers across a region or the world can share knowledge around their crops without relying on the grid and hardwired phones/Internet to do so.

This also centralizes costs to one "host" and minimizes it to the community, so a farmer could send one SMS (free to receive, costs to send), and the host would re-broadcast it to the entire "community." With Twitter already showing that it can (technically) report earthquakes faster than the earthquake itself spreads, this rebroadcasting tool also has clear applications in emergency announcements, citizen journalism and a myriad of other fields.

Technology or Development?

So, was this technology salon about technology, or was it about development projects? Sure, all of the projects discussed at the salon happened to use server and cloud-based SMS technologies. They also use paper, physical transportation, and people. That the technology is now moving from the focus of a project to being a (cool, exciting, powerful, still new-and-shiny) tool in the toolbox is truly heartwarming.

It means mobile phone ICT solutions are maturing into a cross-sector role and not into another silo, but a "pillar of excellence".

Are you a Technology Salon subscriber on the West Coast that's feeling left out of our two SMS4D Salons in Washington DC? Don't! We're bringing all the great SMS text messaging fun to San Francisco with SMS4Dev-SF on June 17th.

Mobile phone payment in India

At mission*social, the Inveneo offices on Mission Street in SoMa, we'll have the following three discussants explaining how they're utilizing humble text messaging to change lives in the developing world:

1. Robert Munro will explain how he's developed machine-learning algorithms to categorize free-form SMS to a 95% accuracy - across any language - for SMS:Medic
2. Zach Berke will showcase a SMS verification system that Exygy helped build which protects against pharmaceutical counterfeiting in India and a new SMS micropayment platform for solar power installations
3. Wayan Vota will expand on SMS:Gov, an innovative use of SMS text messaging to create a 311 system for local governments

If you'd like to join us, you'll need to RSVP for this Salon via SMS: text SMS4Dev, your name, your organization to the live SMS:Gov demo at (202) 506-0148. For those that need an example, I would send "SMS4Dev, Wayan Vota, Inveneo" (w/o quotes).

SMS4D-San Francisco
June SF Technology Salon
Thursday, June 17, 8:30-10am
mission*social Conference Room
972 Mission Street, 5th Floor
San Fransisco, CA 94103 (map)

We'll have espresso and donuts for a morning rush, but be sure to RSVP ASAP, as we only have room for 15 people, then there will be a waitlist. In DC, we're filling up the same day as the announcement goes out.