Dealing with agents’ behaviour in the decision-making process

Gathering a group of managers or executives (decision-makers) in a same place and at a same time is not an easy task. In fact, the decision-makers’ schedule is so tight that it becomes necessary to develop tools that will aid in the communication and in the decision-making process. The intelligent systems (IS) can be the solution to overcome these necessities. In literature, there have been appearing more and more IS that make use of multi agent systems (MAS) in order to represent real decision-makers in this type of systems. In our work we address the problem of how agents should behave during the decision-making process and what strategies they can follow to represent the interests of the decision-maker. We intend to define valid behaviours for agents in group decision-making context and to relate the theoretical behaviours definition with usual attitudes and acts that are relevant for this context. We define two dimensions and relate them with two facets based on the Five Factor Model. Then we propose the behaviours classification according three different levels (low, moderate and high) for each one of the dimensions. We use the value of the personality trait correspondent to each facet in order to classify our behaviours in the scale.This work is part-funded by ERDF - European Regional Development Fund through the COMPETE Programme (operational programme for competitiveness) and by National Funds through the FCT - Fundação para a Ciência e a Tecnologia (Portuguese Foundation for Science and Technology) within project FCOMP-01-0124- FEDER-028980 (PTDC/EEISII/1386/2012) and SFRH/BD/89697/2012.