AUTHOR=Rahmanti Annisa Ristya , Yang Hsuan-Chia , Bintoro Bagas Suryo , Nursetyo Aldilas Achmad , Muhtar Muhammad Solihuddin , Syed-Abdul Shabbir , Li Yu-Chuan Jack 

TITLE=SlimMe, a Chatbot With Artificial Empathy for Personal Weight Management: System Design and Finding

JOURNAL=Frontiers in Nutrition

VOLUME=Volume 9 - 2022

YEAR=2022

URL=https://www.frontiersin.org/journals/nutrition/articles/10.3389/fnut.2022.870775

DOI=10.3389/fnut.2022.870775

ISSN=2296-861X

ABSTRACT=As the obesity rate continues to rise persistently, there is an urgent need to develop an effective weight-loss management strategy. Nowadays, the development of Artificial Intelligence (AI) and cognitive technologies coupled with the rapid spread of messaging platforms and mobile technology with easier access to internet technology offers professional dietitians an opportunity to provide extensive monitoring support to their clients through a chatbot with artificial empathy. This study aims to design a chatbot with artificial empathic motivational support for weight loss, called "SlimMe," and investigate how people react with a diet bot. SlimMe infrastructure was built using Dialogflow as the Natural Language Processing (NLP) platform and LINE mobile messenger as the messaging platform. To simulate the artificial empathy responses, we proposed a text-based emotion analysis to recognize the user emotion. A preliminary evaluation was performed to investigate the early-stage user experience after 7-days simulation trials. Our preliminary evaluation revealed that having an artificially empathic diet bot for weight loss management was a fun and exciting experience. The use of emoticons, stickers, and GIF images made the chatbot response more interactive. Moreover, the motivational support and persuasive messaging features enable the bot to express more empathic and engaging responses to the user. In total, there were 1007 bot responses from 892 user input messages. Of these, 67.38% (601/1007) of the chatbot generated an accurate response to a relevant user request, 21.19% (189/1007) inaccurate responses to a relevant request, and 10.31% (92/1007) accurate responses to an irrelevant request. Only 1.12% (10/1007) of the chatbot does not answer. We present the design of an artificially empathic diet bot as a friendly assistant to help users estimating their calorie intake and calories burned in more interactive and engaging ways. To our knowledge, this is the first chatbot designed with artificial empathy features, and it looks very promising in promoting long-term weight management. More user interactions and further enhancement of data training and validation will improve the bot's in-built knowledge-base and emotional intelligence-base.