Using Genetic Algorithm to Optimize Social Behaviors in the Pattern-of-Life Simulation Open Access

Abstract

Social networks play a crucial role in individual well-being and social dynamics. This thesis explores the feasibility of using an evolutionary algorithm to study the optimal human attributes for maintaining strong social networks, through an agent- based simulation framework called Patterns-of-Life simulation (POL). We implemented a custom Genetic Algorithm within POL that allows agents to reproduce or exit the simulation based on the strength of their social connections. Six key attributes—age, education level, financial status, interest, joviality, and food need—were analyzed. We ran two sets of experiments: one with only survival pressure caused by social networks, and the other with an additional financial pressure introduced through rising housing prices. Our results show that agents with high education level and financial status are more likely to maintain a strong social network and financial sustainability. Agents with moderate food needs and balanced joviality also had better outcomes. The simulation framework also functions as an evolutionary toolbox to study how populations respond to external changes and selection pressure over time. This demonstrates the utility of evolutionary agent-based modeling in studying complex social systems like social networks. 

Table of Contents

Contents 

1 Background ….. 1 

1.1 Social Network and Agent-Based Modeling (ABM) . . . . . . . . . . 1 

1.2 Agent-Based Patterns-of-Life Simulation (POL) . . . . . . . . . . . . 2 

1.3 Evolution and Genetic Algorithm .................... 4 

2 Analyze Social Networks in Evolutionary Perspective…………….. 5 

2.1 Approach ................................. 5 

2.1.1 The logic of social network in simulator. . . . . . . . . . . . . 5 

2.1.2 Agents in Simulator........................ 6 

2.1.3 Agents evolution with Genetic Algorithm . . . . . . . . . . . . 8 

2.1.4 Dataset Generation, Processing and Visualization . . . . . . . 12

2.2 Experiments, Results, and Analysis ................... 13 

   2.2.1 Parameters ............................ 13 

   2.2.2 Results and Analysis ....................... 14

3 Analyze Social Network in Evolutionary Perspective with Financial Survival Pressure…… 22 

3.1 Approach(The Change of House Rental Price). . . . . . . . . . . . . 22 

3.2 Experiments, Results, and Analysis ................... 24

4 Discussion …………..31 

4.1 Summary of Analysis........................... 31 

4.2 Limitation and Future Direction..................... 32 

5 Conclusion ………….34 

Bibliography …………35 

About this Honors Thesis

Rights statement

• Permission granted by the author to include this thesis or dissertation in this repository. All rights reserved by the author. Please contact the author for information regarding the reproduction and use of this thesis or dissertation.

School	Emory College
Department	Computer Science
Degree	B.S.
Submission	Honors Thesis
Language	English
Research Field	Computer Science
Keyword	Social Simulation Genetic Algorithm Evolutionary Computation Social Networks Agent-Based Modeling
Committee Chair / Thesis Advisor	Dr. Andreas Züfle, Emory University
Committee Members	Dr. Jed Brody, Emory University Dr. Joon-Seok Kim, Emory University

Last modified

Primary PDF

Thumbnail	Title	Date Uploaded	Actions
	Using Genetic Algorithm to Optimize Social Behaviors in the Pattern-of-Life Simulation ()	2025-04-19 19:40:57 -0400	Press to Select an action Download

Supplemental Files

Thumbnail	Title	Date Uploaded	Actions