Towards a self-steering conversational agent (“chatbot”)
An opportunity to apply for a funded full-time PhD in the Department of Computer Science and Creative Technologies, UWE Bristol. The studentship will be funded by the Faculty of Environment and Technology and University’s IT Services. Ref 1920-OCT-FET03
Expected start date of studentship: 1 October 2019
Closing date for applications: 28 July 2019
Interview date: to be confirmed
About the Studentship
An offshoot of personal digital assistants are AI powered messaging-based conversational agents (CAs), popularly called chatbots, which have been receiving significant attention in the last few years. However, chatbots are still in their nascent stage. They have a low penetration rate, despite their eventual potential, which raises the question whether it can be due to their design and quality attributes.
While the HCI community has studied how conversational agents are used in different settings, little is done to underpin criteria based on which a CA would suit a particular context, topic or business problem. More precisely, how to evaluate a CA ‘chat’ thread, and steer it towards an optimised position, continuously.
This research will therefore focus on exploring, experimentally, ‘what makes a machine-produced conversation good/effective/entertaining’ according to inspected quality attributes, including, eg resolution, engagement, penetration, success rate of topic suggestion, predictability, medium, etc.
The student will work as part of a team, together with the supervisors and an existing team of researchers, including PhD students, within UWE Bristol's Computer Science Research Centre and closely with researchers from Bristol Robotics Laboratory and UWE’s IT Services.
For an informal discussion about the studentship, please email Dr Hisham Ihshaish on firstname.lastname@example.org
The studentship is available from 1 October 2019 for a period of three and a half (3.5) years, subject to satisfactory progress and includes a tax exempt stipend, which is currently £15,009 per annum. In addition, full-time tuition fees will be covered for up to three years (Home/EU rates only).
Please note: International applications are accepted but the studentship will only cover the full time home/EU fees and the applicant would be expected to fund the remaining amount each year. Please see ourfor up-to-date information.
This is a three and a half year, full-time commitment. The project is ideal for a self-motivated and enthusiastic student with a good honours degree (2:1 or equivalent) in computer science, applied mathematics or other relevant field, and evidence of further study at Masters level or equivalent in a relevant field. Ideally the candidate has a strong interest in machine learning, and AI in general.
Applicants from outside the EU may apply for this studentship but will need to pay the difference between the ‘home/EU’ and the ‘Overseas’ tuition fees. As part of the application you will be required to confirm that you have applied for or secured this additional funding.
How to apply
Please submit your application online. When prompted use the reference number 1920-OCT-FET03. You will need to upload your research proposal, degree certificates and transcripts and proof of as attachments to your application, so please have these available when you complete the application form.
The closing date for applications is 28 July 2019.
If you have not heard from us by 10 August 2019, we thank you for your application but on this occasion you have not been successful.