Exploring the role of data science in assisting UN relief efforts in Syria

2 min read

I recently had the fascinating experience of a visit to the Information and Analysis Unit (IAU) part of the Regional Office for the Syria Crisis in the Office for the Coordination of Humanitarian Affairs (OCHA). The purpose of this mission was to hear first-hand from OCHA staff about their work in Amman, Jordan.

OCHA has for some time been at the forefront of integrating digital tools and data into humanitarian response. As well as developing the reliefweb portal, and the Humanitarian Data Exchange, OCHA has partnered with the MicroMappers;community to crowdsource information collection in the aftermath of disasters such as the recent Typhoon Ruby in the Philippines. They have even developed a dedicated data format for crisis data, the Humanitarian Exchange Language.

It goes without saying that providing humanitarian assistance to those affected by the ongoing Syrian crisis, now in it’s fifth year, is an immensely challenging and complex task. In addition to 3.9 million refugees housed in camps and host communities in Lebanon, Jordan, Turkey, Iraq, and Egypt, 7.6 million others have been displaced within the country itself and 12.2 million people are in need in Syria.

 

The Data Landscape in and around Syria

Accordingly, there is an interesting data landscape surrounding the crisis itself. Zaatari camp itself is remarkably well mapped and understood. REACH, an international NGO specialising in data and information in complex humanitarian situations and UNHCR;have produced very detailed maps of the camp such as this one measuring the density of households as well as the distance to medical facilities, time of arrival and many other indicators. REACH also provides valuable information on the situation within Syria via key informant interviews within Zaatari camp.

Interestingly, these rely heavily on information received from within Syria via social media and messaging services such as WhatsApp. In fact it is even possible to purchase SyriaTel phone credit from stores within the camp and access the Syrian network from the elevated parts of the camp. It was the opinion of several people experienced with working with displaced people that such a novel modality of information gathering can and should be replicated in other contexts.

 

Prototyping dashboards pulling in social media posts

Global Pulse and the OCHA team identified several opportunities to augment the existing information flows based on in-person surveys by using social media. An emerging use of social media in this context is that of sharing information between civilians within neighbourhoods, which often includes information relevant to OCHA’s needs assessments. Facebook is a popular information-sharing mechanism with pages often relating to small tight-knit neighborhoods and communities in Syria.

A screenshot is shown above from very early stage prototype dashboards that came out of our working sessions. Rather than manually checking many Facebook pages periodically, this prototype automatically grabs text from Facebook pages in a Google spreadsheet and marks them on a Google map. This work is simple to implement and should save time for busy staff. We will share more details as the prototype and other collaborations develop.

 

Above: A simple prototype that grabs text from Facebook pages maintained in a list in a shared Google spreadsheet and marks them on a Google map

Top image: The main throroughfare through the Zaatari Camp, Jordan known by residents as ‘Champs-Élysées’ 

 

Did you enjoy this blog post? Share it with your networks!

News, thoughts and ideas about big data and AI, data privacy and ethics from across the Pulse Lab Network. Read more on the blog.

Pulse Lab Kampala

Dialogue is the Key- Shaping AI for Africa

At UNGP, we believe in dialogue. This is why we participated in the Conference on the State of Artificial Intelligence in Africa (COSAA) held in March 2023. The conference was

Scroll to Top