Given the interesting ways in which users type and choose menu options, this type of automation is incredibly helpful in getting them where they need to be. For instance, whether someone types the word one, or punctuated variations of the number one, the bot is able to understand the intent behind what they are saying, and respond appropriately.
The Covid-19 chatbot that saved lives
Some of the work behind the WhatsApp service that provided millions around the world with crucial Covid-19 info. In partnership with Praekelt.org.
Engineering | Feersum Engine | Design | Content | Client Partnership
We don’t often get the chance to work with our sister company Praekelt.org these days, but this partnership was something of a silver lining during a cloudy and chaotic time.
They asked us to help them with a few things on the Covid-19 chatbot they built for the National Department of Health, which is essentially – and we don’t use that word lightly – a WhatsApp-based helpline that supports people with Covid-related health queries, and points them in the direction of accurate info if needed.
The bot was picked up by the World Health Organisation as well as several governments including Australia, New Zealand, Ethiopia and Mozambique. To date it has graced the palms of well over 20 million people.
Most of the props lie squarely at the feet of Praekelt.org, but we’re honoured to have been involved with some of the innovation, as we were asked to share our experience and expertise in automation, Natural Language Understanding (NLU) and exploratory data analysis.
Real-time data insights
Our exploratory data analysis (EDA) with topic modelling and phrase clustering means that we can quickly analyse conversation logs and make modifications if necessary. In this case, it has supported effective decision-making in South Africa’s response to Covid-19.
The data analysis technology currently being developed allows companies like DStv, Absa and MTN to get fast and effective feedback from the people using their chatbot services. But exploratory data analysis is not the only technology that has contributed to one of the world’s most used chatbots. Response automation, machine learning and NLU have also played their parts.
Natural Language Understanding (or machine comprehension) allows the bot to have conversations with a user, answering their queries based on frequently asked questions. It provides potentially life-saving information in multiple local and international languages. At the same time, it eases the pressure on call centres, because the automation means we can help more users than is humanly possible.
The most used WhatsApp bot in the world.
As an NPO, Praekelt.org has turned this into the largest non-profit service to use WhatsApp for Business. HealthAlert is also freely available to any ministry of health worldwide.
of users within three days of launching
of people guided through the pandemic within three weeks