The Cybersmile Foundation wanted to develop a completely scalable and sustainable support solution for people affected by cyberbullying and online abuse on a global level. They envisaged a chatbot that could identify the needs of users and provide them with appropriate advice while signposting them to expert support organisations in their local area — wherever the users are in the world. Cybersmile also told us about their ambition to have the system deploy on partners’ websites and apps in the future.
We came up with a system architecture that used an embeddable chat interface and could be installed unobtrusively on any website, starting with the Cybersmile site. The interface would allow users to send text or audio through to an AI platform that we would programme to understand users’ requests and respond accordingly. We would also produce a user-friendly content management system that would allow the Cybersmile team to curate helpful, relevant and safe content that could be presented to users once the bot had identified their needs.
Cybersmile Assistant is for anyone
seeking help or information
Ai provides safe environment
to talk and seek advice
Resource library educates,
guides and helps
To give Cybersmile’s team a structure that would allow them to begin building a library of content to be delivered to users via the bot, our team started by building the CMS. It was important that all users could navigate the system without technical knowledge and without having to get involved with the complexities of AI. Content types were created for articles, advice, organisations and helplines, each with their own specific data fields. We also made it possible to restrict content to specific regions. This important distinction would allow Cybersmile to ensure that the helplines that were delivered were appropriate to the user’s location and that articles would use localised spellings.
While Cybersmile worked on their content library, we built the interface through which users would communicate with the chatbot. Our design team’s intuitive solution — a fullscreen overlay that could be triggered by a button that floated in the corner of the website — would work well on both desktops and mobile devices. This approach worked great on the Cybersmile site, but it was also chosen for its portability, as it could be added with relatively minor customisation changes to Cybersmile’s partner websites in the future.
260Conversations and guidance results
“As a parent what can I learn about the effects of online activity and anxiety?”
The last piece of the puzzle was to develop the conversational routes within the AI software. The main body of the conversational logic was focused on identifying the core topic of a user’s query (be that “depression”, “anxiety” or even “crisis support”). We worked with the Cybersmile team to train the AI to understand a wide range of ways that a person may describe their problem when reaching out for support.
Once the bot could identify the topic of people’s problems, we could then ask them to refine what they were looking for by suggesting the range of content types available. By combining the topic, content type and user’s location, the bot could then find and return suitable content from the Cybersmile CMS.