Date of Award

2011

Publication Type

Master Thesis

Degree Name

M.Sc.

Department

Computer Science

Keywords

Computer Science.

Supervisor

KKobti, Ziad (School of Computer Science)

Rights

info:eu-repo/semantics/openAccess

Abstract

Emotions are an integral part of human decision making so it is important to integrate emotions into artificial agents to make them more realistic. In this thesis we intend to design and implement an artificial emotional response agent simulation using three psychological models for emotions and develop a corresponding algorithm for each depicting its process in order to find a suitable algorithm. After comparing the performance of the three algorithms we use Ortony, Clore and Collins(OCC) theory to generate emotions in a case study of a basic Hospital Simulation System. In this, there are patient and nurse agents who trigger emotions due to interaction with each other. Results show that OCC algorithm is advantageous when specific emotion has to be generated and is more accurate than other algorithms. Also from the experiments performed for the case study show that an increase in emotional stress leads to higher error rates in nurse task performance when their logical performance is compared with emotional performance.

Share

COinS