How users of social networking services (SNSs) dynamically identify their own reasonable strategies was investigated by applying a co-evolutionary algorithm to an agent-based game theoretic model of SNSs. We often use SNSs such as Twitter, Facebook, and Instagram, but we can also freeride without providing any content because providing information incurs costs to us. Numerous studies on evolutionary network analysis have been conducted to investigate why people continue to post articles. In these studies, genetic algorithms (GAs) have often been used to find reasonable strategies for SNS users. Although the evolved strategies in these studies are usually common among all users, the appropriate strategies for them must be diverse because the strategies are used in various circumstances. In this paper, we present our analysis using a co-evolutionary algorithm, multiple-world GA (MWGA), the various strategies for individual agents involving co-evolution with their neighboring agents. We also present the fitness value we obtained, a value that was higher than those obtained using the conventional GA. Finally, we show that the MWGA enables us to observe dynamic processes of co-evolution, i.e., why agents reach their own strategies in different circumstances. This analysis is helpful to understand various users’ behaviors through mutual interactions with neighboring users.