Work
opacity arrow
Covid-19 Information Assistant
Case Study

Using automation to help the National Department of Health deliver life-saving information

How Natural Language Understanding (NLU) and exploratory data analysis helped create a WhatsApp helpline.
Challenge
We were asked to share our experience and expertise in advancing Praekelt.org’s Covid-19 chatbot for the National Department of Health.
Solution
We used automation, Natural Language Understanding (NLU) and exploratory data analysis to help create a WhatsApp-based helpline to support people with Covid-related health queries.

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.

Response automation

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.

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.

Response automation

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.

Machine learning + NLU

Natural Language Understanding (or machine comprehension) allows the bot to have conversations with a user, answering their queries based on Frequently Asked Questions (FAQ). 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.

large image 1large image 1

"

large image 2large image 2

Result

As an NPO, Praekelt.org turned this into the largest non-profit service to use WhatsApp for Business. HealthAlert was also freely available to any ministry of health worldwide.

1 M

Users within three days of launch

20 M

People helped in three weeks

Give Helm Chat™ a go in real time

Powered by Helm Engine™