Case Studies

CARE

CARE launched two chatbots to promote childhood immunization

Summary

CARE launched two chatbots on WhatsApp, one in Bangladesh and one in Nigeria, to promote childhood immunization. The chatbots successfully disseminated immunization knowledge in engaging, yet easy-to-use formats.

Challenge

CARE is a global leader within a worldwide movement dedicated to ending poverty. CARE works around the globe to save lives, defeat poverty, and achieve social justice.

In Bangladesh, the government’s successful programs to increase knowledge about immunization against infectious diseases saw a decrease in performance during the height of COVID-19. As the Extended Programme on Immunization (EPI) centers reopened in 2022, the CARE Bangladesh team wanted to provide people with immunization knowledge and increase the number of mothers using EPI services to secure immunization for their children.

In Nigeria, infectious diseases that could be prevented through vaccination cause thousands of deaths annually, yet 40% of children go unvaccinated during a crucial age for early immunization. Since 2021, CARE Nigeria’s Lafiyayyen Yara (Healthy Child) project has worked to reduce infectious diseases in children under the age of 5 in the northeastern state of Yobe. To amplify their programming, CARE Nigeria conducted digital social and behavioral change communications (SBCC) campaigns promoting early childhood vaccination in collaboration with Yobe state social media influencers. The team also wanted to create an automated system of vaccine information delivery to their target population.

Solution

With support from Meta, CARE built automated chatbots through the Turn.io platform that delivered important early childhood immunization information to people in Bangladesh and Nigeria. The chatbot’s visibility was boosted by a Facebook ad campaign that ran from December 2022 to February 2023.

Content development for the chatbot began with an assessment of what information surrounding immunization was most important for people to access.

Bangladesh’s ad campaign consisted of locally designed static and video ads that used engaging animations, trusted messengers, and persuasive copy emphasizing that immunizations were free. Each ad was linked to the chatbot.

A vaccine calendar ad provided valuable information on when children needed to be vaccinated, and generated the highest number of post engagements.

Nigeria’s ad campaign consisted of static ads that used imagery from Nigerian social media influencers and evocative copy emphasizing that immunizations were for free. Each ad was linked to the chatbot. Nigeria also drew on inspiration from Bangladesh’s top performing vaccine calendar ad.

Both campaigns consisted of three phases. The first and second phases advertised the chatbot, the third and final phase retargeted chatbot users and promoted the chatbot’s survey feature.

Results

Both campaigns ran from December 2022 to February 2023.

Bangladesh results

The chatbot and ad campaign reached 34.2 million people across Bangladesh and resulted in 123,918 unique conversations started.

14% (17,318 people) opted in to receive future immunization-related messaging from the CARE country office.

An in-platform survey to gain user feedback found that 89.7% of people reported that they would recommend the chat service to others.

Post engagements totaled 662,722 and had an overall share rate of 0.083% (which is higher than CARE’s benchmark).

Conversation lengths averaged around 5.7 messages per user.

Nigeria results

The chatbot and ad campaign reached 3.6 million people, mainly in northeastern Nigerian states, and resulted in a total of 15,000 unique conversations being initiated.

18% (2,700 people) opted in to receive future immunization-related messaging from the CARE country office.

An in-app survey to gain user feedback found that 76.6% of respondents said they would recommend the chatbot to their family or friends.

CARE Nigeria garnered a total of 95,400 post engagements and had an overall share rate of 0.037%, which is higher than the benchmark.

Yobe state, where CARE Nigeria’s offline programming is targeted, saw the highest engagement rate (39.5%) compared to other regions.

Conversation lengths averaged around 9.7 messages per user, +70% longer than the conversation length seen in CARE Bangladesh’s chatbot.

Learnings

Explore Meta’s messaging solutions to deepen audience engagement and start meaningful conversations.

Ensure that the language you choose to use is the best fit for those you are trying to reach. No matter how amazing your chatbot is, if your audience cannot understand the language it’s in, the potential impact could be hampered.

Content needs to be designed to encourage “deep flows”. Ask yourself, how are you creating content that encourages the user to continue interacting? The average user interacts for 2-3 messages. Consider how to provide valuable and impactful content within the first 2-3 interactions as well as how to drive deeper engagement—for example, by including a quiz.

Consider using characters native to SMS and texting such as emojis, concise language, and keywords to make your copy more effective.

Include a ‘help’ catch-all message that directs people to contact information or a number to call in case of an emergency.

Include a call to action to subscribe or opt-in to notifications. This way, you can re-engage users or notify them when new content is available. It also allows you to conduct user surveys in the future.

Supporting quotes

“The chatbot on WhatsApp provided us with a lot more reach than we were ever able to imagine previously. We needed to build the service to be able to reach key stakeholders who influence decision-making within family households. We were able to do that by reaching not only mothers, but also religious and traditional leaders,” said Habeeb Sulaiman, CARE Nigeria’s Communication and Advocacy Officer.

“Many people thought that they were conversing with a human being in a real-time live chat and were expecting a response from the other end to their personalized questions. There were trust issues among the respondents as most were new to this chatbot concept. There was a 24% increase (from baseline to endline) in the understanding of EPI which indicates significant increase in understanding the importance of EPI and its accessibility,” said Tanzin Labonno, Senior Technical Officer-Monitoring & Evaluation, Urban Health unit of CARE Bangladesh. “Qualitative assessment could be helpful to understand the effectiveness and acceptance of the chatbot in the communities to improve it further to cater to people’s needs.”