Application of simple recommendation model to diverse populations

Abstract

In Today’s modern Industrial cities we see that, many people having different cultures share the same settlement and form a typical social complex system. People come from other cities or even foreign countries and form an ethnically diverse population. Newcomers bring their daily habits and other cultural values such as clothing styles, meals, likes and dislikes. As a result of interacting with other people some cultural values change and completely forgotten while others become popular and known by the majority of people. There should be a mechanism helping some cultural values and choices being more popular and causing other people being assimulated by majorities and this mechanism may not be simple as because of their population sizes. Instead, there may be some other factors such as peoples’ choice of interactions with other groups. The work done in this M.S. thesis extends the Simple Recommendation Model (SRM) that is firstly introduced by H. Bingöl in 2006. The new model diversifies in two points: That is, recommendations between agents will be made over their choices and selections of recommended agent will be made according to the recommender agent’s cpreference of interactions. The research made by Wimmer in 1998 about the native Swiss and immigrants’ interactions among each other will be used for empirical data. In our model, agents will be grouped according to their national origin and initially will keep their own choices in their memories. Then, they will begin to interact with each other and with other groups. They will remember and forget the choices by an exchanging mechanism. As a result some choices will emerge to be known by the majority of people while some others will completely be forgotten. We will try to predict which group’s choices are likely to become popular and which group’s choices are likely to be forgotten and the reasons not mentioned.