Any views expressed within media held on this service are those of the contributors, should not be taken as approved or endorsed by the University, and do not necessarily reflect the views of the University in respect of any particular issue.

Conversational interfaces at the University of Edinburgh

Most technology horizon reports these days seem to have a common reference: Conversational interfaces. Whether a chatbot, a voice assistant or any other machine-learning driven interface, this appears to be the next frontier in audience engagement. To reflect on this, and how these would be useful in a Higher Education environment, we ran a project last year focussing in voice interaction design and standards. It was an interesting journey, with very interesting outputs which are available for all University colleagues.

The main objective of this project was to explore and learn how websites can be designed or adapted for voice search. An additional aim was to develop an experimental application for either the Amazon Alexa or Google Home devices. During our research, it was quickly evident that the conversational interface environment is a bit of a grey area. Most people are excited by the technology, fewer are actively using it and even less have actually made genuine progress in integrating with their web services.

“Speak to Us” – Voice interaction design for University websites – Information Services Projects web pages

First think, then implement

To address this challenge, we took a step back. Apart from looking at the conversational technology landscape, we started exploring potential standards and guidance. As always, it’s all about understanding the problem and designing the right solution, rather than jumping into coding right away.

Our focus was not only to understand what is available, but to offer this insight back to the University community. This has now been achieved by publishing the findings in a series of wiki pages, which are split in four areas:

Focuses on how to build a Conversational Interface, from the ground up: Define the Business Logic, Design and Test the Conversational Flow, Build the Natural Language Understanding and, finally Deliver a Text or Voice Interface.

Defines a model to evaluate potential use cases to assist when making a decision to build a Conversational Interface, based on 5 questions:

  1. Does it fit the users?
  2. Will it be useful?
  3. Does it fit our systems?
  4. Can we make it good?
  5. Are these conversations important?

Lists a set of HE use cases around the areas of: Student Entry, Student Support, Student Admin, Staff Admin, Learning Support and Classroom Support. Furthermore, has a list of prototype conversations in video format.

Finally, a look into the current technology landscape exploring the most popular Natural Language, Conversational, Chatbot and Voice platforms.

Whether interesting in building your own chatbot or Alexa skill, I would like to invite you to have a look. They are a really useful and interesting resource, which we will aim to keep up to date.

Conversational Interfaces Workshop

To test this guidance, and to engage with interested University colleagues, we ran a full day workshop at the end of August. The agenda did cover an introduction to Conversational Interfaces and their place in Higher Education. The next step was to evaluate the set of selected 6 use case areas, based on the existing guidance. This was achieved by using the “jobs to be done” methodology.

Jobs to be done. Where marketing meets UX – Blog post by Neil Allison

Conversational Interfaces Workshop

Hard thinking colleagues at the workshop, which resulted in many ideas and conversational design prototypes.

The three ideas that made it to the next stage were:

  • I would hire a product to manage my deadlines (For students)
  • I would hire a product to help me with my studies (For students)
  • I would hire a product to manage my contacts (For Staff)

After lunch time, the attendees were split in groups and asked to design conversations based on the selected use cases. Finally, these ideas were turned into prototypes. All of the teams had a chance to present their ideas back to the wider group.

Two sample Conversational Interface prototype scripts.

Two sample Conversational Interface prototype scripts.

Overall, it was a very productive day. It was very energising seeing people in action, focussing on the problems and design potential solutions. Post-workshop, the feedback was really positive. Attendees thought that stepping back from coding was a great idea, and helped them put thinking about Conversational Interfaces in perspective.

Really appreciated and enjoyed the pace and tone of the presentation. As someone who works in the tech space it is always nice to see new educated perspectives on design.

Conversational Interfaces Workshop attendee

Currently, we ‘re looking into ways on how we can follow up on this project. This, potentially, would include development of a prototype solution using on of our use cases.


Leave a reply

You may use these HTML tags and attributes: <a href="" title=""> <abbr title=""> <acronym title=""> <b> <blockquote cite=""> <cite> <code> <del datetime=""> <em> <i> <q cite=""> <s> <strike> <strong>


Report this page

To report inappropriate content on this page, please use the form below. Upon receiving your report, we will be in touch as per the Take Down Policy of the service.

Please note that personal data collected through this form is used and stored for the purposes of processing this report and communication with you.

If you are unable to report a concern about content via this form please contact the Service Owner.

Please enter an email address you wish to be contacted on. Please describe the unacceptable content in sufficient detail to allow us to locate it, and why you consider it to be unacceptable.
By submitting this report, you accept that it is accurate and that fraudulent or nuisance complaints may result in action by the University.