Don't miss our weekly PhD newsletter | Sign up now Don't miss our weekly PhD newsletter | Sign up now

  Emotionally intelligent artificial conversational agents for higher education or healthcare

   Computer Science

This project is no longer listed on and may not be available.

Click here to search for PhD studentship opportunities
  Dr Arthur Money  Applications accepted all year round  Self-Funded PhD Students Only

About the Project

Artificial conversational agents, can be embodied (physical robots or digital avatars on a screen) or not embodied (chat-bots or digital assistants). Agents may be able to converse but they can also appear ‘empathetic/emotionally intelligent’ when they talk, and in the case of embodied agents they can also deliver non-verbal communication (body language/facial expressions). In the higher education domain, viva assessments (oral examinations) are used frequently to assess candidates on their work and have many benefits for both the student and the assessor. For example, providing: the opportunity to carry out highly personalised/tailored assessment, unique insight into student ability and understanding, probe depth of knowledge, ensure authenticity of submitted written work, and provide real-time feedback on performance, to name a few. Viva assessments, however, are known to cause anxiety, particularly as a result of the social interaction and in particular face-to-face interaction with an assessor/lecturer, that a traditional viva setting demands. Although there is some evidence in the field of Human-Computer Interaction (HCI) and agent-based interaction research that suggests that interaction with artificial agents can elicit lower levels of anxiety compared with a human equivalent, there is a need to explore the pedagogical value of using intelligent (emotionally intelligent or similar) artificial agents to carry out viva assessments within the higher education domain. Whilst this advertisement sets the backdrop to the area in which the successful PhD candidate could position their research, there is much scope for tailoring this topic to the successful candidate’s specific knowledge, interests, and skills. Similarly, there is significant scope to explore the use of intelligent conversational agents within the area of healthcare research, for example, exploring the value of using artificial agents in the context of talking therapies (e.g. psychotherapy, psychoanalysis, cognitive behavioural therapy, cognitive analytic therapy), if this is an area that is more in line with the successful candidate’s interests.

Hence, we invite applications from candidates that have an interest in exploring the value of using intelligent conversational agents within the context of higher education or healthcare. It is envisaged that the successful candidate would design, develop, and evaluate a prototype conversational agent (embodied/not embodied, possibly using wizard of oz techniques) and trial it within the chosen higher education/healthcare context.

Candidates should have good software development and prototype design and development skills. Experience of carrying out user-centred research and collecting and analysing both qualitative and quantitative data is also desirable.

Computer Science (8) Mathematics (25)

Funding Notes

Brunel offers a number of funding options to research students that help cover the cost of their tuition fees, contribute to living expenses or both. See more information here: The UK Government is also offering Doctoral Student Loans for eligible students, and there is some funding available through the Research Councils. Many of our international students benefit from funding provided by their governments or employers. Brunel alumni enjoy tuition fee discounts of 15%.

How good is research at Brunel University London in Computer Science and Informatics?

Research output data provided by the Research Excellence Framework (REF)

Click here to see the results for all UK universities
Search Suggestions
Search suggestions

Based on your current searches we recommend the following search filters.