ALMA: Machine learning breastfeeding chatbot

Abstract

Since the first computer, researchers always try to simulate human behave. For Chatbots, one of the first goals is to interact with the user like a human using Natural Language. For Health chatbots, another goal is as much important: be able to provide the correct answer to the user request. Over Years, many health chatbots have been developed for many fields such as cancer, diagnosis orientation, psychiatrics, etc. breastfeeding companion are, however, rare (only two breastfeeding chatbots). In this paper, we have developed ALMA, a Breastfeeding Chatbot (BC) that can converse with a breastfeeding mom throw natural language understanding (NLU) and natural language generation (NLG), and provide her – breastfeeding mom – with the relevant information using AIML knowledge base and CNN pre-trained model. We made ALMA available for a normal WhatsApp conversation throw Twilio API. ALMA was tested by volunteering breastfeeding moms and the results validated by breastfeeding consult.