Ohifeme Eitokpah
The main aim of the project is to determine how effective a persuasive chatbot application could be when providing health-based suggestions to users. Chatbots aim to replicate human interaction but struggle due to limited responses and an inability to maintain user interest. A persuasive chatbot aims to replicate a personal human interaction by either developing an AI capable of learning social cues or by containing a large database of responses to users.
The Agile methodology was implemented used to develop the project. Since it focuses on different iterations of a product and improving on the product iterations over time.
Research has shown the major issue of chatbots is ineffective communication. This issue has not prevented the chatbot from functioning properly but has been a hindrance to the efficiency of the chatbot application. To address this issue a persuasive chatbot will possess a great degree of social skills to encourage user interaction, answer user questions and alleviate any concerns.
In conclusion, a persuasive chatbot application is not easy to develop and requires an incredibly large database of information or a very complex AI. But despite these issues, they are outweighed by the benefits. Over time all other issues can be fixed.
Ohifeme Eitokpah
HOW EFFECTIVE IS A CHATBOT BASED HEALTH APP IN PREDICTING AND PERSUADING HEALTHY SUGGESTIONS
What Are You Researching?
The research is focused on how effective a chatbot application would be in improving healthy behavior in patients. In order to encourage someone to improve their behavior a certain amount of persuasion and motivation is needed. Chatbots are capable of reaching a large number of people but lack the persuasion and motivational skills to encourage people. But what could happen if chatbots could be improved to a point in which they can encourage users? How many lives could be improved with beneficial medical information?
Why Are You Researching It?
The world has many doctors but it has more patients. The challenge in this would be the number of individuals who engage in unhealthy habits, those who are in need of medical assistance but cannot get in quick enough or possess underlying illnesses they may not be aware until too late. To properly address this challenge some medical institutions have developed applications and websites that incorporate chatbots which mainly provide information to users. But what could happen if these chatbot applications could be developed to such a level in which they could persuade the user to stop engaging in unhealthy habits and motivate them to continue in case they begin losing motivation.
How was the research undertaken?
Research information was gathered mainly from articles on Google scholar that focused mainly on the relationship between humans and chatbots, challenges people face with chatbots, human persuasion and the development of a persuasive chatbot applications.
Studying the relationship between humans and chatbots: Since many websites and apps implement chatbots it has become common to use them. Some studies have shown different issues from both the human and chatbot. When focusing on the human issues it includes an over dependency on the chatbot in some users for medical diagnosis which can at times be incorrect (mainly in chatbot applications that provide medical checkups) and some other users who prefer to engage with a doctor in person and not that interested in using a chatbot. While some issues with the chatbot include incorrect information (mainly in chatbot applications that provide medical checkups), limited responses leading to dissatisfied users who have questions, only available online and a level of distrust from users and medical professionals
Studying human persuasion: This study focuses mainly on human interaction and how to persuade others to engage in something. There were many studies on these especially in sales. Many stated that a welcoming personality, the ability to assure the customer that they are making the right choice, a well-known brand that they can trust and word of mouth.
Studying the development of a persuasive chatbot application: The most crucial study of this project focused on how feasibly persuasive a chatbot could be. The application is in fact possible and a few are attempting to develop it. Many big tech companies have chatbot like assistants such as Microsoft’s Cortana, Apples’ Siri, Google Assistant and many more. But a developer named Justine Cassel who is working on a chatbot application with social intelligence. The study shows that despite the difficulty developing such an application it was very successful when interacting with users and with some development could one day be a persuasive chatbot.
Benefits of the Chatbot Application
The application will mainly serve as a digital assistant to users like Siri, Google Assistant, Cortana, and many others but in a more personal way. The chatbot will possess different tones of voice and responses to users, human-like interactive skills to help users feel like the chatbot application is capable of being a friend. Despite the difficulty of developing this application, the benefits are too great not to try.
Results and Findings
Some studies conducted have shown that people respond well to chatbot applications when they possess some necessary features. One such study was a chatbot application named Sara. Tagged as the descendant of Alexa and Siri, this chatbot is capable of reading different features of the user in order to respond appropriately. Sara was capable of studying facial expressions, tone of voice, and other features.
Another study of a persuasive chatbot stated that persuasion is an active attempt by one person to change another individual's mind, beliefs, concept, or attitude. In order to achieve this goal, there are steps that need to be taken starting from assessing the situation and needs of the person being persuaded, building rapport, focusing on benefits, listening to and addressing concerns, accepting the limitations, finding common ground of acceptance, and clarifying terms. These skills comprise both verbal and non-verbal components which help in communication.
Conclusion
The research has shown that a chatbot application can be very effective in persuading individuals. Some companies have already begun developing such advanced chatbots but even they struggle to properly reach that goal. So far very few have developed such a chatbot such as Sara. But with some improvements it is possible to create a chatbot application that can serve as a friend, assistant or guidance support to users. With such a role in users lives they will be able persuade them more effectively.
Acknowledgment
I would like to express my gratitude to the teaching staff and Lancaster University Ghana who have given me the opportunity, support and guidance to develop this project. My family members who have been a source of moral support and GOD who gave me the strength to not dropout of this course.
References
Drees, J. (2021). The future of healthcare chatbots: Physician replacement or enhancement? https://www.beckershospitalreview.com/innovation/the-future-of-healthcare-chatbots-physician-replacement-or-enhancement.html
Futurist, T. M. (2021). The Top 12 Health Chatbots. https://medicalfuturist.com/top-12-health-chatbots/
Knight, W. (2016). Chatbots with Social Skills Will Convince You to Buy Something. https://www.technologyreview.com/2016/10/26/156438/chatbots-with-social-skills-will-convince-you-to-buy-something/
KRZYSZTOF, M. (2020). Chatbots in Healthcare: Benefits, Risks, and 5 Insightful Use Cases. https://codete.com/blog/chatbots-in-healthcare
Lagasse, J. (2020). Proper implementation of chatbots in healthcare requires diligence. https://www.healthcarefinancenews.com/news/proper-implementation-chatbots-healthcare-requires-diligence
Leah. (2021). What Do Your Customers Actually Think About Chatbots? https://www.userlike.com/en/blog/consumer-chatbot-perceptions
Martin Adam, Michael Wessel & Alexander Benlian Martin Adam, M. W. & A. B. (2021). AI-based chatbots in customer service and their effects on user compliance. https://link.springer.com/article/10.1007/s12525-020-00414-7
Srivastava, D. (2021). Top Benefits, Risks and Challenges of Chatbots in Healthcare. https://www.nimbleappgenie.com/blogs/challenges-of-chatbots-in-healthcare/
Slide 1 image (max 2mb)
Slide 1 video (YouTube/Vimeo embed code)
Image 1 Caption
Slide 2 image (max 2mb)
Slide 2 video (YouTube/Vimeo embed code)
Image 2 Caption
Slide 3 image (max 2mb)
Slide 3 video (YouTube/Vimeo embed code)
Image 3 Caption
Slide 4 image (max 2mb)
Slide 4 video (YouTube/Vimeo embed code)
Image 4 Caption
Slide 5 image (max 2mb)
Slide 5 video (YouTube/Vimeo embed code)
Image 5 Caption
Slide 6 image (max 2mb)
Slide 6 video (YouTube/Vimeo embed code)
Image 6 Caption
Slide 7 image (max 2mb)
Slide 7 video (YouTube/Vimeo embed code)
Image 7 Caption
Slide 8 image (max 2mb)
Slide 8 video (YouTube/Vimeo embed code)
Image 8 Caption
Slide 9 image (max 2mb)
Slide 9 video (YouTube/Vimeo embed code)
Image 9 Caption
Slide 10 image (max 2mb)
Slide 20 video (YouTube/Vimeo embed code)
Image 10 Caption
Caption font
Text
Image (max size: 2mb)
Or drag a symbol into the upload area
Image description/alt-tag
Image caption
Image link
Rollover Image (max size: 2mb)
Or drag a symbol into the upload area
Border colour
Rotate
Skew (x-axis)
Skew (y-axis)
Image (max size: 2mb)
Or drag a symbol into the upload area
Image description/alt-tag
Image caption
Image link
Rollover Image (max size: 2mb)
Or drag a symbol into the upload area
Border colour
Rotate
Skew (x-axis)
Skew (y-axis)
Image (max size: 2mb)
Or drag a symbol into the upload area
Image description/alt-tag
Image caption
Image link
Rollover Image (max size: 2mb)
Or drag a symbol into the upload area
Border colour
Rotate
Skew (x-axis)
Skew (y-axis)
Image (max size: 2mb)
Or drag a symbol into the upload area
Image description/alt-tag
Image caption
Image link
Rollover Image (max size: 2mb)
Or drag a symbol into the upload area
Border colour
Rotate
Skew (x-axis)
Skew (y-axis)
Image (max size: 2mb)
Or drag a symbol into the upload area
Image description/alt-tag
Image caption
Image link
Rollover Image (max size: 2mb)
Or drag a symbol into the upload area
Border colour
Rotate
Skew (x-axis)
Skew (y-axis)
Image (max size: 2mb)
Or drag a symbol into the upload area
Image description/alt-tag
Image caption
Image link
Rollover Image (max size: 2mb)
Or drag a symbol into the upload area
Border colour
Rotate
Skew (x-axis)
Skew (y-axis)
Image (max size: 2mb)
Or drag a symbol into the upload area
Image description/alt-tag
Image caption
Image link
Rollover Image (max size: 2mb)
Or drag a symbol into the upload area
Border colour
Rotate
Skew (x-axis)
Skew (y-axis)
Image (max size: 2mb)
Or drag a symbol into the upload area
Image description/alt-tag
Image caption
Image link
Rollover Image (max size: 2mb)
Or drag a symbol into the upload area
Border colour
Rotate
Skew (x-axis)
Skew (y-axis)