Hacking Hunger Episode 11: pinpointing hunger with mobile phones

In the latest of their ‘hacking hunger’ podcast series, WFP USA’s M.J. Altman talks to Jean-Martin Bauer about  how mobile phones in the hardest-to-reach corners of our world are changing how we understand and fight hunger.

In the podcast Bauer discusses how his 12 years as a humanitarian worker stationed in West Africa inspired him to think about using mobile phones to gather food security data. He touches on using mVAM methods in emergencies like Iraq and tackling gender disparities in mobile phone use, and also discusses how mVAM shares the data it collects with the communities it serves as well as wider humanitarian community.

Check out the podcast below, or subscribe to “Hacking Hunger” on iTunes, Stitcher, Soundcloud, and TuneIn Radio.

 

 

 

From open data to #ZeroHunger

whatsapp-image-2016-09-15-at-13-20-50

At WFP’s Vulnerability Analysis and Mapping (VAM) unit we constantly strive to make our data as open as possible. We’ve previously guest blogged for the Open Data Institute on when open data isn’t enough’ about why it’s so important to us. We are therefore excited to participate in the Global Open Data for Agriculture and Nutrition (GODAN) summit taking place this week in New York. GODAN supports the proactive sharing of open data to make information about agriculture and nutrition available, accessible and usable.

During the summit world leaders, researchers, students and organizations will come together to illustrate the importance of agriculture and nutrition open data to get to Zero Hunger. We are excited to meet other like-minded people and share the technology and open processes that we’ve been experimenting with to contribute to Zero Hunger.

What are we showing at the GODAN summit?

If you have time to pass by our exhibit you can explore, alone or guided by a data analyst, our databank and our interactive data visualizations on our food security analysis websites including the mVAM monitoring website.

godan-demo-ivrOur exhibit also shows some of the technology we are using to gather data from the world’s most vulnerable communities. You can test our chatbot prototype or participate in an IVR demo of the food security surveys we use to get information from poor communities. If you complete the survey, we’ll tell you Food Consumption Score, one of the core indicators that WFP uses to measure food security, and match you with an mVAM respondent based on your age and gender.

GODAN runs from September 15-16, and we’ll be sharing our experiences of the conference on social media, so make sure to follow along on Twitter at @mobileVAM!

Chatbot: back to the drawing board

alice-hand-model

We’ve recently developed a prototype of a chatbot to communicate with people via the Telegram messaging app, but it will eventually work on any messaging app. The purpose of a prototype is to test our approach thus far in the real world and then go back to the drawing board to improve it. Before this month, our testing had been limited to our colleagues here in Rome and our partners at InSTEDD.  However, we really needed feedback from people in the communities we are actually trying to reach.

Eventually we’ll test a later version of the chatbot in the countries where we work. But for some initial feedback, we were able to get in contact with people right on our doorstep, who had completed a difficult journey to Rome. UNHCR recently estimated that there are roughly 65.3 million people currently forcibly displaced worldwide. Instability and conflict in the Middle East and Africa has led many to flee to Europe in the hope of a safer, better life. One of the most used and most dangerous routes is via Libya and then across the Mediterranean Sea to southern Italy. To give you an idea of the scale, between 29 August and 4 September this year, Italy averaged over 2000 arrivals every day. Of those who reach the mainland, many make their way north to Rome. There are now many centres across the city that provide refuge, often in the form of meals, language learning and legal support.  

UN photo/UNHCR/Phil Behan

We went to one of these migrant centres to speak with people and get their feedback on whether the chatbot would be useful in their home communities. We can hear migration statistics but listening to people’s stories really made these statistics come alive. One person we talked to described being saved by the Italian Coast Guard as the ship transporting him sunk in the Mediterranean. He said he will always be grateful to the Italian government for his rescue.

So needless to say, we were very grateful that people would take time and test the bot. Its is currently in English so we were only able to test it with English speakers right now. The goal is to get it running well in English and then translate and adapt it to other languages.

First we asked people a couple of questions about smartphone ownership in their country of origin. They told us that while the poorest people in rural areas don’t have smartphones around 70% of the population does – meaning that we can still communicate with a lot of people via smartphone. They then had a go at using our chatbot, first answering the food security survey and then trying out the price database. Here are a few things that speaking with them helped us realize:

Simplify our questions and build up to them more. We know we spend a lot of our time working with food security surveys and we know our food security questions by heart. We can forget how weird they can sound to everyone else, especially over a chat. For our participants, it was the first time they’d seen something like this so they were at times confused about how to respond to the questions about their diet or their coping strategies. They were especially confused because the questions seemed to come out of nowhere, with no build up or putting them in context. By the second time around, they went through the survey much quicker, but we need to make sure to get the best first time responses. We need to speak normal language, not make everyone else try to speak our specialized jargon.

No one wants to interact with a robot: make the chatbot as chatty and friendly as possible. Our participants also advised us that it would be good to add some slang and colloquial language. But it is important to have it to feel like as natural an interaction as possible: As one of them said: “ If I want to say something or someone to talk to, I can write, and the chatbot can help and I can relax.’

Make it as intuitive as possible. The chabot users will have different backgrounds and tech literacy. Right now, as one of our participants put it, it’s accessible for “any educated person’, but we don’t want to limit our target audience. Our users might not even have secondary education so we want anyone who can use facebook to find it straightforward.img_2350

Make sure the bot recognises typos! Everyone knows how easy it is to make a typo on your smartphone so it’s essential that our chatbot recognises a few of the easy ones. When we ask people how many days in the past week that they ate vegetables for example, it’s pretty easy to give ‘3 days’ ‘three days’ ‘three’ and ‘3days’ and all mean the same thing! Even potentially typos like “theee days” or ‘three dyas”. We need to integrate these differences in text and typos as acceptable responses, asking for confirmation when needed, so we get the best results.

Put the bot on different messaging apps. One of the reasons why they were a bit hesitant with the bot at the beginning was the fact that they were not used to the Telegram app. It’s important for the bot to run on the app people use most. This can vary depending on the country, so when we do our pilot, we need to put the chatbot on the most commonly used messaging app.

Give people food price information for their areas. At the moment, our bot automatically reads the general WFP food price database. Whilst this is a cool way of looking at food prices all over the world, it’s not actually that useful on a day-to-day basis. Our participants said that knowing up-to-date regional prices would be great – as it would allow them to go to different parts of the country to buy food if the price was particularly low there. As we are already collecting high frequency price data, we want to be able to integrate this into the chatbot. This would be a great way to use the real-time data that we collect to give directly back to the people we collect from.

Overall the participants were positive to the bot as it stands, even saying that they think it’s ‘really cool’. However, there’s a lot of work to be done to make it more user friendly. Using this feedback we are going back to the drawing board. We hope to have an even better version for our official pilot in sub Saharan Africa later this year. We are very grateful to the people who helped us test this last week. They have much more pressing things to worry about so we thank them again for generously giving us a bit of time.

Our Harvard Humanitarian Initiative Guest Blog

Food Security and the Data Revolution: Mobile Monitoring on the Humanitarian Front line

26 August 2016 – Harvard’s Advanced Training Program on Humanitarian Action (ATHA) blog by Jean-Martin Bauer, Brittany Card & Alice Clough

IMG_2322

Obtaining real-time and actionable information on the needs of affected populations has long been a priority for humanitarians; so keeping up with new technologies that could improve existing data collection systems is also a necessity. Innovations such as mobile phones and the Internet have already profoundly changed the nature of humanitarian work. They are proving to be faster and cheaper than legacy information systems, increasing the amount of information that decision makers have, and ultimately enabling them to save more lives.

However, what is truly transformative is their potential to reach previously ‘invisible’ populations. An estimated 3.2 billion people now have access to the Internet, and in developing countries more households have access to a mobile phone than clean water and electricity. New digital tools such as online messaging and social media are offering a participatory approach to data collection, energizing legacy monitoring systems. Rather than the traditional top down, institutional form of early warning that focuses on only collecting beneficiary information, they offer a more ‘democratic’ and citizen-led model (Mock Morrow and Papendieck). More vulnerable people are now able to make their voices heard, giving them the agency to make humanitarian systems more effective and suitable for their needs…

Read the full article here.

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’.