XClose

UCL Institute of Health Informatics

Home
Menu

New paper: Sex differences in fitness to practise test scores

21 September 2018

Often in public health, we want to persuade people of some course of action, like doing more exercise...

If we are to improve our arguments or do research on how a computer might be taught how to make arguments,  we need a supply of examples. A new study by Lisa Chalaguine, a PhD student in UCL Computer Science, with colleagues from the Institute of Health Informatics and the E-Health Unit, offers a new approach, which the team call argument harvesting. This uses a chatbot - an automated computer programme - to enter into a dialogue with a participant to get arguments and counterarguments from him or her. As it is automated, the chatbot can rapidly collect a large body of examples. The chatbot was tested in a case study looking at attitudes of women to participation in sport.

Chalaguine LA, Hamilton FL, Hunter A, Potts HWW. Argument harvesting using chatbots. InComputational Models of Argument – Proc. of COMMA 2018Frontiers in Artificial Intelligence and Applications 2018; 305, 149-60. doi:10.3233/978-1-61499-906-5-149. Available at https://arxiv.org/abs/1805.04253