Towards Human Argumentation [Self-Funded Students Only]

Keywords: Cognitive Biases, AI, Artificial Intelligence, Argumentation

Background

Negotiating, deliberating, discussing, persuading – we experience these every day; they are all examples of argumentation. It is a very multidisciplinary fields, and the focus of this project lies on the intersection of computer science and cognitive science.

Convincing people to do or not to do something is not easy. Consider, for example, a doctor persuading a patient to drink or smoke less, or a teacher persuading a student to organize their work and time better. The way these problems are approached often need to take into account the nature of the person we are trying to persuade to do or not to do something. Very rarely there is a one-fits-all approach. Humans are fallible and suffer from various cognitive biases that affect how they process information and how likely they are to agree or disagree with it.

Developing computational approaches that are able to engage in meaningful and convincing discussions with humans is therefore a challenging topic. It is however one with many applications in healthcare, finances, driving safety, and more. An increasing number of companies is developing various systems and chatbots with the aim of interacting with the users in order to achieve a particular goal, which is particularly important in areas such as healthcare that are facing staff shortages.

Aims, Methods and Deliverables

The goal of this PhD is to focus on developing methods that would detect biased behaviour in human agents and offer argumentation models to handle it, with the end aim of increasing success rates of persuasive dialogues. The student will employ various computational argumentation and cognitive science techniques, as well as other AI approaches as needed.

It is expected that the student will deliver new scientific methods, carry out experiments with human participants and prepare a prototype dialogue system in an application domain of their choosing. Possible examples include a system that encourages smoking cessation.

Contact for information on the project, please contact Dr Polberg, [Email Address Removed]

Academic criteria: A 2:1 Honours undergraduate degree or a master's degree, in computing or a related subject.  Applicants with appropriate professional experience are also considered. Degree-level mathematics (or equivalent) is required for research in some project areas.

Applicants for whom English is not their first language must demonstrate proficiency by obtaining an IELTS score of at least 6.5 overall, with a minimum of 6.0 in each skills component

This project is open to students worldwide.

How to apply:

Please contact the supervisors of the project prior to submitting your application to discuss and develop an individual research proposal that builds on the information provided in this advert. Once you have developed the proposal with support from the supervisors, please submit your application following the instructions provided below

This project is accepting applications all year round, for self-funded candidates via https://www.cardiff.ac.uk/study/postgraduate/research/programmes/programme/computer-science-and-informatics 

In order to be considered candidates must submit the following information: 

• Supporting statement 
• CV 
• In the ‘Research Proposal’ section of the application enter the name of the project you are applying to and upload your Individual research proposal, as mentioned above in BOLD
• Qualification certificates and Transcripts
• Proof of Funding. For example, a letter of intent from your sponsor or confirmation of self-funded status (In the funding field of your application, insert Self-Funded)
• References x 2 
• Proof of English language (if applicable)

If you have any questions or need more information, please contact [Email Address Removed]