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.
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.
Result
Users within three days of launch
People helped in three weeks
