Can mobiles be used to monitor nutrition?

WFP/Trust Mlambo

We told you in a recent blog post that we will be adding nutrition indicators to the existing data that we collect using our mobile modalities. We are thrilled to announce that this is finally happening!

Monitoring nutrition: why it’s important

Undernutrition is a huge global problem. Worldwide, 800 million people are calorie deficient and about two billion suffer from micronutrient malnutrition – not having the essential vitamins and minerals. Women and young children are at the greatest risk – nearly half of all deaths in children under five, or 3.1 million child deaths annually, are linked to undernutrition. Malnutrition in the first 1,000 days (from conception to child’s 2nd birthday) can cause irreversible damage to children’s brains and growth.

We have recently seen a lot of high-level political commitments to address undernutrition. However, one of the biggest challenges to turn the commitments into action has been the lack of timely data for effective programming. This is where our mVAM modalities could help: voice calls, SMS or IVR could be used to collect data for nutrition surveillance (especially in hard-to-reach areas). Potentially, mVAM tools could help provide real-time information to help manage nutrition programs. Over the coming months, we’ll try testing this approach.

Mobile data has worked for food security indicators. Will it work for children’s nutrition?

WFP/Nancy Aburto

In the past, we have tested various mobile methodologies to demonstrate that it can be used to gather credible data on food security. In the last few years whilst expanding to 26 countries we’ve learnt that remote data collection is fast, cost-effective and the most efficient way to collect information, especially in hard-to-reach areas. The results of our experiments show that live voice calls and SMS are complementary and can be useful in different contexts. We are testing both how both mobile methodologies could collect data on nutrition indicators. In Southern Africa, we are going to be trying a nutrition survey using SMS and in Eastern Africa, we will be comparing the results on nutrition indicators from face-to-face and live phone call interviews.

The challenge of monitoring nutrition by mobile

3-Mica Jenkins

WFP/Mica Jenkins

To date, mVAM has collected information about household food consumption and coping strategies. This usually involves calling randomly selected people. We also call trusted key informants that tell us about food security in their community. Nutrition is different because we’re looking for information about women of reproductive age and children under five. Mothers of children of that age are also a relatively small group, and the challenge will be reaching such a small demographic and ensuring  their participation.  

How do you actually monitor nutrition?

You might be wondering how we go about monitoring nutritional status. Undernutrition results from a combination of immediate, underlying and basic determinants – diseases and inadequate dietary intake are the two immediate determinants of undernutrition, and food security is one the three underlying determinants of undernutrition. While there are many underlying causes of undernutrition, dietary quality is a very important determinant of nutritional adequacy; therefore our efforts will be focused on monitoring dietary quality of women and young children.

2-Mica Jenkins

WFP/Mica Jenkins

In the first phase, in line with the 1000 days initiative,  we will be testing two internationally validated indicators. The first indicator we have decided to collect data on is Minimum Acceptable Diet (MAD) (MAD).  This is one of the globally validated indicators to assess Infant and Young Child Feeding (IYCF). It collects information on both the minimum feeding frequency and the appropriate minimum dietary diversity for various age groups. The other indicator we are going to collect is the Minimum Dietary Diversity-Women (MDD-W) that collects information about whether or not women 15-49 years of age have consumed at least five out of ten defined food groups the previous day or night. This will allow us to assess the diversity of women’s diets, an important dimension of their diet quality. This information is crucial, not just because inadequate dietary intake is an immediate cause of undernutrition, but also because dietary diversity is correlated with many other aspects of food insecurity. Eventually, we will also explore using other indicators of maternal and child undernutrition, as well as other mobile methodologies.

We’re aware that others have tested mobile to collect nutrition data (see an interesting paper in the mHealth series about testing SMS for IYCF indicators in China, published in 2013). We look forward to building on these lessons. We are very excited to collaborate with our internal and external partners to test the indicators. Stay tuned to know more about how we are bringing an innovation in nutrition and food security monitoring!

VAM Talks: Episode 7

Logo2Bienvenue au VAM Talks en français! Ce premier épisode présente mVAM et son utilisation au Burundi.

 

Live from Rome – meet the people behind the numbers!

 

Yesterday, we had the chance to present our work through a live broadcast on Facebook.  As you may know, southern Africa is in the midst of a severe drought, and many of the countries in the region have declared a state of emergency.

WFP’s Vulnerability Analysis and Mapping (VAM) unit, which mVAM is a part of, is responsible for collecting different types of data that WFP and its partners use to inform their humanitarian responses. Meet the different teams within VAM as we explain what we do and how our work is used in the context of the southern Africa drought.

Voice calls in Niger: when basic works best

Niger 4

WFP/ Cecilia Signorini

As many of you know, mVAM has expanded considerably in the last few years and we are now present in 26 countries. You may be familiar with high profile places we work in like Syria, or those where we are testing out new technologies like Haiti. We therefore wanted to write an update on one country that we haven’t spoken about in a while: Niger.

What is WFP doing in Niger?

To give you a reminder of why we are working there here’s a quick rundown. Niger is a landlocked low-income country in the Sahara-Sahel belt with a population of over 16 million people. Every year the United Nations Development Programme (UNDP) does a Human Development Index based on indicators of income, health and education indicators and Niger has ranked 188 out of 188 for the last few years. WFP estimates that 2.5 million people in Niger are chronically food-insecure. Increasing regional instability has only worsened the situation. Niger is currently responding to two emergencies: the recent Malian civil war in the north and Boko Haram in the south east whose insurgency and systemic violence has forced even more people to move, destroying community assets and food reserves. The volatility of this situation means that getting accurate food security information is both incredibly important and unfortunately very difficult. To get some more information from the ground we spoke to Moustapha Touré, who works on VAM and Monitoring and Evaluation (M&E) in WFP’s Niger country office. For the full interview (in French) watch out for an upcoming episode of our VAM Talks series, our podcast about how WFP sources its food security data.

Why mVAM?

The country office in Niger was keen to add extra dimensions to their food security analysis, and with insecurity rife in and around Diffa, it made sense to try remote monitoring.  Moustapha was the VAM officer in Goma where mVAM started in 2013, and when he arrived in Niger, his ideas and experience helped him to establish mVAM in the country, which quickly flourished. In our blog last September we wrote about how the team in Niger scaled up from their pilot surveys in the refugee camps working with a Niamey-based call center, iTelCom. This call center is pretty special – they are actually based in Niger’s first and only start-up incubator. By working with them, we are also contributing to the emergence of a local start-up specializing in digital engagement in vulnerable communities.  

niger-blog

WFP/VAM

The call center had begun placing calls to refugees from Mali in the camps of Abala and Mangaize in early 2015. One of the advantages of mVAM is ‘no boots on the ground’: we can conduct food security surveys without having to put anyone in the line of fire. When increasing attacks from Boko Haram meant it became urgent to get data from Diffa, the corner of Niger on the Lake Chad basin, our partner was able to ‘shift’ to this new area with relative ease, thanks to their prior experience.

mVAM and displacement

The complexity and longevity of the insecurity affecting Niger means that ‘displacement’ has many different meanings. Populations have been moving in and out of the country for so long that it’s sometimes almost impossible to define them as a ‘refugee’ a ‘returnee’ or an ‘internally displaced person’ (IDP). Many of the Malian refugees in the north are pastoralists whose livelihoods depend on moving around with their livestock so living in an enclosed refugee camp is even more of an issue. To try and solve this problem new areas have been designated as ‘Zones d’accueil des réfugiés’ (ZAR) or refugee hosting areas. Unlike a standard camp setting, they are open spaces where displaced people have room to graze animals, allowing them to continue their traditional lifestyle. In Diffa, recent Boko Haram attacks have caused a new wave of displacement in June raising the total to more than 240,00 displaced people in the region. All of this means that the questions we have in our food security surveys about a household’s displacement status is not nuanced enough to provide us with any useful answers. So we were wondering how the team in Niger is dealing with this complex landscape in terms of their implementation of mVAM.

Niger 5

WFP/Cecilia Signorini

Moustapha said one way of coping with this was making sure to “conduct face-to-face surveys before mVAM” to get some prior information about the households. This information serves as a base which they can use to monitor the movements of the populations. They also change their terminology, making sure they only refer to “forced displacements” to specify that they only want to know about the movements because of a specific shock rather than seasonal movements. The reason this works in Niger is because the only mVAM modality used is our live calls so more time can be taken explaining this terminology than with SMS. Sometimes basic really works best!

In fact, this baseline information has already come into use. One area that has suffered from a recent attack is Bosso, resulting in a large amount of displaced households. As Moustapha pointed out, via mobile phones we can maintain a direct line to the affected populations, wherever they happen to be. Based on their responses, “we can see when they moved, whether they moved just once or if they are constantly moving or returned”. This might sound a bit CIA but the information is actually really useful for WFP operations. With a better understanding of affected populations we can make sure distributions are in the best places.

Challenges ahead?

Niger 1edit

WFP/Cecilia Signorini

Whilst the system is working quite well there are always areas that can be improved. We spoke before about the challenges of mobile coverage in this largely rural context, so they are talking to the phone companies to try and get better coverage. There are also issues in terms of female responses. Less than 5 percent of women own their own
mobile
and some women don’t have the right to use a phone to receive a call without their husband’s permission, otherwise they could invite accusations of adultery or subversion of their husband’s authority. WFP’s West Africa Regional Bureau is working hard to try and solve some of these issues, exploring the possibilities of using female operators or using face-to-face recruitment.

We don’t think we will be using our fancy IVR and chatbots in Niger anytime soon, but it does look like mVAM is set to stay. As well as continuing the regular data collection in Diffa, Moustapha and the team plan to expand countrywide.

Introducing our Chatbot

bot pictureAn important part of our job at mVAM is to stay tuned into the developments in the rapidly evolving mobile technology sector. Lately we noticed two main trends: first, more and more people in the places we work are using smartphones and chat apps to communicate, leading us to think about how to better reach out to this segment of the population. Second, chatbots, robots that live in chat applications, are all the rage and have a big potential to contribute to our work.

What is a chatbot?

A chatbot is a computer programme that uses artificial intelligence to interact with users through a messaging service in a way that is designed to seem like a conversation. We’ve been experimenting with ways to expand our capacity for two-way communication, i.e. contacting local communities but also hearing back from them. A chatbot provides a friendlier, more responsive way to interact with people by letting them communicate more naturally, in a “chat” as the name implies. As well as answering the chatbot’s questions, users can also ask the chatbot simple questions.

Since we piloted mVAM in 2013, we’ve collaborated with InSTEDD, a nonprofit design and technology company that develops innovative open source tools for social impact. For three years, we used their SMS and IVR software to collect food security information. So when we wanted to delve into using chatbots, it was only natural that we reached out to them. Of course, not everyone we want to survey will have access to a smartphone. A large proportion of people using messaging apps at moment are young, urban, and male, introducing a bias to our surveys. But as smartphone ownership becomes more prevalent this won’t always be the case. This technology is really promising so we want to stay on top of it and see how it can be used for humanitarian purposes. As a first step, we want to use a chatbot to conduct a mobile food security survey on a messaging app. At the moment we are using Telegram because they have an API, which allows developers to easily build customized tools, but we are designing the bot so that it can be used on other messaging apps.

Here’s what our chatbot with InSTEDD would look like. Respondents are contacted on Telegram via their smartphones and asked a series of questions, about their food security and livelihood situations just like they would be by phone, SMS, or on our other mVAM modalities.

Check out our chatbot demo:

Why are we so excited about chatbots?

Chatting on a messaging app lets us collect new types of information. People can send our chatbot pictures, voice notes and geolocations that would enrich our food security analysis. As part of our analysis we ask people socio-demographic questions about things like their roof type, which give indications about a household’s economic status. Using the chatbot we can actually get pictures of these answers! We’ll literally see and hear about the situation on the ground and get to double check where these pockets of food insecurity actually are.WhatsApp-Image-20160721

It’s cheap! Not only does the chatbot have the potential to reach more people, the format is also cheaper than SMS, IVR and Live Calls.

It’s way more fun. The chatbot can process more complex sentences and respond more dynamically, letting the user drive the conversation. There’s a whole spectrum of things a chatbot can be programmed to do anything from a stilted, regimented conversation where users can only answer in a certain way, to natural language processing where users can chat as they would with a human. We think the technology just might not be there yet to meet our needs for a completely natural chat- we followed the Microsoft chatbot problem closely. However since we are only focusing on a specific topic we are opting for something in the middle- that allows us to get the food security information we need but also give users a natural, fun experience.

It lets us share more information. The chatbot can automatically read WFP’s food price database and tell people about the food and commodity prices where they live and give information about any big changes in the last few months. This database is so detailed that we can actually provide this information down to the market level in many countries!  Every time a new dataset is added to the original database, the chatbot automatically updates its price information, ensuring that local communities can access the latest information.

It’s flexible. The chatbot doesn’t have to just be used for prices. Users could ask WFP questions about our food distributions or programmes – whatever information we are able to insert in our database. This way we can provide a great incentive for people to complete our surveys, giving our beneficiaries a chance to give us feedback on the services we provide, and sending them a variety of information at a low cost.

Our chatbot is still a prototype, but we will let you know how our testing goes before we roll out our first pilot.

VAM Talks: Episode 6

Logo2The team heads to a Hackathon in Amsterdam where we challenged data scientists to apply their skills to humanitarian problems and ‘hack hunger’.

The El Niño Aftermath: Tracking Hunger in the Millions in Southern Africa

We’ve been writing a lot about how mVAM can help in conflict situations where whole areas are cut off because of violence or an epidemic (see our blogs on Yemen, Somalia, Iraq and article on Ebola). But over the past year, the world was disrupted by another type of event- a climatic one: El Niño. The El Niño weather pattern results from a warming of sea temperatures in the Pacific roughly every three to seven years. This El Niño was one of the strongest on record.  The reason why El Niño was so concerning is its global reach, it didn’t just affect the Pacific; places as far away as Guatemala, Pakistan, Indonesia and Ethiopia were all at risk of floods and/or droughts. While the El Niño itself has abated, it has left millions hungry in its wake (current estimates are that 60 million people are food insecure globally). And a La Niña year is looming.

One area that has been particularly affected is Southern Africa. Across the region, this year’s rainfall season was the driest in the last 35 years. Most farmers are facing significantly reduced and delayed harvests.

El Niño hit when Southern Africa was already vulnerable to food insecurity. The region had already experienced a poor 2014-15 harvest season, meaning that food stocks were already depleted. Now, after El Niño, roughly 41 million people are classified as food insecure. On 13 June 2016 WFP categorized the region as an L3 emergency – a situation requiring the highest level of humanitarian support. We’re therefore dramatically expanding our national food security monitoring in the region so WFP can quickly provide as much relevant food security information as possible to effectively respond to the crisis.

Predictions that this El Niño would have a big effect had already started coming in 2015 so we began setting up mobile monitoring in countries that were particularly vulnerable to El Niño. We started in Malawi which had very disruptive weather patterns looming (potentially too much rain in the north and huge rainfall deficits in the south). We lacked current household data to track the impact on food security across the country.

To get information quickly and cheaply, we started a monthly SMS survey with GeoPoll in December 2015. And Malawians sure were quick to respond! In 24 hours, we had 1,000 questionnaires completed.  When analyzing the results, we wanted to make sure people were understanding our texts. The adult literacy rate in Malawi is only 61.3% so we kept the questionnaire short and as simple as possible. We included questions for one food security indicator- the reduced coping strategy index (rCSI) which asks people about the coping strategies they are using when they don’t have enough to eat. We also checked that the data made sense, and in general, the rCSI behaved as we would suspect. It was correlated with people’s messages about their community’s food security situation and their wealth status. As with all of our surveys, we are continually improving them. In this case, we increased our sample size and district quotas to capture more people in rural areas.

Monitoring Maize Prices

IMG_0095Market prices, especially maize prices, are key to Malawians’ food security. Maize is the staple food, used to make nsima which is consumed daily. So to monitor market prices in 17 hotspot districts, we collected phone numbers from over 100 traders in 51 markets throughout Malawi. We first tried asking them prices by text message, but we didn’t receive many responses.  It seems like sending back a series of texts is a bit too much to ask of traders who volunteered out of their own good will to participate in our market survey. We therefore set up a small call center in WFP’s country office. We trained two operators, and they were quickly placing calls to traders every week. When they could just answer a quick phone call instead of having to type in answers, traders willingly reported current commodity prices.

Our latest report from June 2016 shows that maize prices are now between 50 and 100 percent higher than this time last year. This is having a big effect on Malawians. As you can see from our word cloud, alarmingly ‘not-enough’ featured prominently in our open ended question about maize.

word cloud_cropped

Nutrition Surveillance for the first time

In most countries, we have been concentrating on household level indicators like food consumption. But health centers treating malnutrition could potentially give us important indications of the nutrition situation of different parts of the country. In Malawi, WFP works with health centers to address moderate acute malnutrition (MAM) in Malawi by providing fortified blended foods. So to make the most of our call center, we decided to call these health centers every two weeks and track malnutrition admission data for children (aged 6-59 months) and for adults with HIV/AIDS or tuberculosis. In the first six weeks of monitoring, we saw a big increase in the number of moderate acute malnutrition admissions for children increased greatly where severe acute malnutrition rates did not show a clear pattern. We dug further, and the Ministry of Health had initiated mass screenings to enroll malnourished children in nutrition programmes which generally pick up moderately malnourished children. With health center admission data, it’s important to check what else is going on in the country. We’re hoping to soon pilot contacting mothers of malnourished children about their children’s progress to gain additional insight into the nutrition status of vulnerable populations in Malawi.

Now that we have Malawi firmly established, we’ve started reporting on Madagascar and our data collection is ongoing in Zambia, Lesotho and Mozambique. So watch this space for more news about how we get on in these next few months.

Test Complete: 6 things we learned about online surveys

IMG_3030

Photo: WFP/Catherine Clark

We told you in a recent blog post that we were testing online surveys in Haiti to get an idea of urban food security perceptions. This was very new for us so here’s a quick follow up on what we learned:

1. Get ready to experiment! For online Surveys (and pretty much anything else we do), this is our approach. We don’t have that much experience designing community level questions so we decided to throw in a variety to see what worked and what didn’t. Our question asking respondents to name two main difficulties faced by poor people probably worked the best so we’ll keep that in. However, we also asked if poor people’s quality of life had improved, worsened, or stayed the same in the past 3 months. Almost everyone said “worsened”  but we weren’t sure if we were really capturing a trend. Given that our respondents were generally pretty wealthy, they might automatically put this response when they are asked about poor people.

2. Re-iterate! Your questions will need tweaking. In our case, street food is an important part of urban Haitians’ diet so we asked a question on the price of a plate of spaghetti. The survey format meant respondents couldn’t free type any answers so we gave them price ranges. It turns out these were a bit too wide as almost all the responses were in one range. However, now that we know the approximate range, in the next round we can put specific numbers in and allow respondents to select an exact value.

3. Tailor your questions to your respondents. You might not actually know that much about them the first time so think about who your respondents will be and what they can realistically answer. Again, a lot of this comes through trial and error. We asked about wage rates for a male manual worker and for a female domestic worker, but our
respondents were mostly young, male and well-educated so they had no idea about how much these people get paid. Age gender

We’d also really like to know about migration so we tested a question. But daily migratory flows in Haiti aren’t very big so back to the drawing board with this idea.

4. Use partial responses. People will drop out of the survey as it goes on. However, we still wanted to use all of the information they did give us, especially since this was a qualitative survey.

5. Be patient. Expect a steady volume of responses, but it could take some time to reach your target. We averaged about 30 completed questionnaires a day. Our target was 750 completes so it took about 5 weeks.

IMG_3242

6. Reaching poor areas is always a challenge. It’s still difficult to get enough responses from poor areas. We knew that going in, and sure enough, in Haiti’s biggest slum, we did not have many responses.

As always, we’ve learned a lot while experimenting. We’re looking forward to revising our questionnaire and giving online surveys another go!

DRC Data Challenge: Brainstorming Solutions with CAID

image_mkengela discussion

We just spent three days with the fabulous CAID team from the DRC government.  We’ve been working with CAID, DRC’s Center for the Analysis of Development Indicators, since January to establish mKengela, a national market monitoring system using mobile technologies. We contracted a professional call center in Kinshasa to call traders twice a month to ask about food prices. For more info check out our mKengela blog entry and our first market reports:

Bulletin_Information _marchés_RDCongo_mKengela_n°2_30May_2016_JBB_2_cropped

But CAID has even bigger ambitions for data collection and analysis in DRC. So the WFP Country office and our team here in Rome decided to organize a technical visit in Rome to collaborate further on data systems. Their coordinator, Grégoire Mwepu and two technical staff, Marc and Bertrand, came to explore solutions for data management and sharing. Sib, our VAM Officer on the ground, attended from our office in Kinshasa.

The result- great brainstorming! Everyone was throwing out ideas.

API and Data Management

image_bertrand discussionCAID is very interested in setting up their own API- we’ve set up an API to share our data. But the rule for an API is get your data management straight first. Once your data is properly structured, then you can throw on an API on top- think of it as the icing on the cake. So we had a lot of discussions on what would be the best solution, not only to manage mKengela market data but all the development data that CAID is collecting across 145 territories on agriculture, health, energy, etc. While CAID works on data management, they can connect to our API for any data we have on DRC.

Automated Processing

CAID has set up an impressive data collection system in 145 territories. But that’s a lot of data. So they were also interested in how to automate as much of the cleaning and analysis process as possible. We discussed what we are doing the Stats Engine we set up to automatically run data quality checks and calculate statistical tests.

Arif (Chief Economist- WFP) and Grégoire (Coordinator- CAID) examine visualizations of DRC data

Arif (Chief Economist- WFP) and Grégoire (Coordinator- CAID) examine visualizations of DRC data

Data Visualization

Like us, CAID is interested in anything that makes it easier for people to understand, especially decision-makers. We also discussed data visualization and showed them our work with Tableau (see our blog entry on experimenting with Data Visuals and Tableau).

mKengala Revisions

After two rounds of market data collection, it was also time to review mKengela. In our previous blog post on mKengala, we were excited that CAID had diligently collected so many local measurements. But it turns out that having so many local measurements of varying sizes is hard to manage. So we’d recommend starting with a longer list and then shortening it to the most commonly used units of measurement after a couple rounds. CAID’s representatives in the 145 territories are also collecting more trader phone numbers since some numbers they had were always turned off or no longer working.

These three days of brainstorming technical solutions were very exciting for us. With mVAM, our priority is to partner with national governments and see how mobile technologies can help their humanitarian and development response.

A huge thanks to Grégoire, Marc, and Bertrand for traveling all the way to Rome. Stay tuned as CAID puts some of the ideas discussed into action and we hopefully have a follow up technical session in Kinshasa later this year.

CAID and mVAM Technical Visit Participants. Thanks CAID for coming all this way!

CAID and mVAM Technical Visit Participants. Thanks CAID for coming all this way!

VAM Talks: Episode 5

Logo2Alice Clough interviews Sid Krishnaswarmy from WFP Uganda about why the country office is adding mVAM to its existing repertoire of food security surveys.