SAGE Labs: Technology experiments to build new bridges to knowledge

This month the Product Innovation (PI) team at SAGE launched the SAGE Labs site that will showcase the experiments and projects that the team are currently working on. Experimenting with cutting edge technologies has the potential to lead to innovative services and opportunities that can build bridges to scholarly knowledge. The PI team will share the results of their short sprints so you can see what they've been up to. We've featured some of these experiments on the SAGE Ocean blog in the past, notably, experimenting to see what kind of information could be drawn out of images on SAGE Journals by using machine learning tools to do object recognition in images. You can read more about this experiment here.

We aim for this site to be a window into the innovation that is happening across all of SAGE
— Ian Mulvany, Head of Product Innovation at SAGE Publishing

Tony, The Study Coach Chatbot


In this experiment, we wanted to build a simple Proof of Concept chatbot using Google DialogFlow to understand whether it would be useful as an alternative way to search through the SAGE resources. We were also interested in exploring how chatbots could offer more conversational interfaces; a more interactive way to solving problems for SAGE readers. 

How did we do it?

We used Google's DialogFlow to build Tony, which does not require advanced coding knowledge. We picked DialogFlow because it is a conversational platform, it allows natural language interactions and supports voice assistants. Another advantage for using DialogFlow is that it can already match similar phrases, and enabled the management of the conversational flow through 'contexts'.

First, we designed a potential conversation for the chatbot. We structured a simple flow and drafted a script of possible phrases and intents. Within the intents (high-level category of action), we added the phrases to train the bot how to respond. For example, if the user talks about giving a presentation, Tony would ask about challenges. This information would then help Tony look for an appropriate resource for that user.

We also fed the chatbot a small list of resources, where it would look for recommendations. This was the final goal of the conversation—to lead the user to an appropriate resource. What did we learn? Read the outcomes here