A User-Centered Chatbot (Wakamola) to Collect Linked Data in Population Networks to Support Studies of Overweight and Obesity Causes: Design and Pilot Study

Abstract

Background Obesity and overweight are a serious health problem worldwide with multiple and connected causes. Simultaneously, chatbots are becoming increasingly popular as a way to interact with users in mobile health apps. Objective This study reports the user-centered design and feasibility study of a chatbot to collect linked data to support the study of individual and social overweight and obesity causes in populations. Methods We first studied the users’ needs and gathered users’ graphical preferences through an open survey on 52 wireframes designed by 150 design students; it also included questions about sociodemographics, diet and activity habits, the need for overweight and obesity apps, and desired functionality. We also interviewed an expert panel. We then designed and developed a chatbot. Finally, we conducted a pilot study to test feasibility. Results We collected 452 answers to the survey and interviewed 4 specialists. Based on this research, we developed a Telegram chatbot named Wakamola structured in six sections: personal, diet, physical activity, social network, user's status score, and project information. We defined a user's status score as a normalized sum (0-100) of scores about diet (frequency of eating 50 foods), physical activity, BMI, and social network. We performed a pilot to evaluate the chatbot implementation among 85 healthy volunteers. Of 74 participants who completed all sections, we found 8 underweight people (11%), 5 overweight people (7%), and no obesity cases. The mean BMI was 21.4 kg/m2 (normal weight). The most consumed foods were olive oil, milk and derivatives, cereals, vegetables, and fruits. People walked 10 minutes on 5.8 days per week, slept 7.02 hours per day, and were sitting 30.57 hours per week. Moreover, we were able to create a social network with 74 users, 178 relations, and 12 communities. Conclusions The Telegram chatbot Wakamola is a feasible tool to collect data from a population about sociodemographics, diet patterns, physical activity, BMI, and specific diseases. Besides, the chatbot allows the connection of users in a social network to study overweight and obesity causes from both individual and social perspectives.

The Use of Artificial Intelligence–Based Conversational Agents (Chatbots) for Weight Loss: Scoping Review and Practical Recommendations

“…Those in the control group underwent 7 in-person counseling sessions with a health care professional, whereas those in the intervention group interacted with the PathMate 2 chatbot daily with 4 in-person counseling sessions (61%) [ 36 ]. Other studies (19/23, 83%) either used chatbots mainly to collect data on diet, physical activity, sitting time, and sleep [ 31 , 32 ] or were still in the developmental stage. Future studies should consider adopting an experimental design that evaluates the use of chatbots on objective weight-related outcomes such as weight loss, diet (eg, food choices, calorie intake, and consumption frequency), and physical activity (eg, energy expenditure, activity type, and activity frequency) using inferential statistics that suggest repeatability.…”

“…Other techniques used in text-based chatbots were the delivery of colloquial, personally and culturally appropriate conversational tones and content [ 26 , 30 ]; emojis to emulate human emotional expressions [ 30 - 32 ]; positively framed words [ 32 ]; citations of credible information sources [ 26 , 33 ]; and validation (eg, acknowledgments and compliments) of not only behaviors but also thoughts and feelings [ 41 ]. Participants of the included studies were also found to have appreciated the personification of the chatbot (eg, funny, animated, empathetic, or playful) [ 25 , 29 , 31 , 32 , 37 ] and the provision of real-time, fast, and reliable recommendations [ 26 , 29 , 38 ]. In addition, studies (9/23, 39%) that enabled speech, instead of just text-based chatbot interactions (including those that use augmented reality [AR]) [ 29 ], improved engagement through a more convenient hands-free voice interaction with the chatbot [ 34 , 43 - 46 ].…”

“…In contrast, users mentioned concerns regarding privacy and accountability [ 43 , 46 ], the inconvenience of having the chatbot on a limited number of third-party platforms (eg, only Telegram that one may not use) information [ 31 ], message or question overload that causes user fatigue [ 25 , 31 ], transparency about the app objectives and information sources [ 31 ], and appearing too robotic (eg, speaking too slowly in a robotic voice). Users also suggested that the chatbots should probe further to explore emotions and action plans instead of prescribing them [ 41 ].…”

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

“…Another example is Forksy, which monitors users' healthy eating behavior ( 13 ). A telegram chatbot Wakamola also serves as a valuable tool to assess individuals' obesity risk based on their sociodemographics, diet, physical activity, BMI, and social lifestyles ( 26 ). A preliminary review of AI chatbot-based physical activity and diet interventions revealed that more than half of the reviewed chatbots successfully deliver behavior change strategies through increased user motivation and engagement ( 27 ).…”

Clinical Decision Support Systems for Palliative Care Referral: Design and Evaluation of Frailty and Mortality Predictive Models

“…After pooling more than 400 members of the UPV community, the final design was selected, including the name of the chatbot: Wakamola. Wakamola is registered in the UPV technical catalogue and produced three research articles: the first one presented the chatbot and the data collected [Asensio-Cuesta et al, 2021a], the second analysed the lifestyle changes registered in the chatbot due to the COVID-19 confinement [Asensio-Cuesta et al, 2021b]. Finally the third article explored the differences between the three pilots performed using Wakamola [Asensio-Cuesta et al, 2021c].…”