Behavioral responses to epidemics in an online experiment: using virtual diseases to study human behavior

Abstract

We report the results of a study we conducted using a simple multiplayer online game that simulates the spread of an infectious disease through a population composed of the players. We use our virtual epidemics game to examine how people respond to epidemics. The analysis shows that people's behavior is responsive to the cost of self-protection, the reported prevalence of disease, and their experiences earlier in the epidemic. Specifically, decreasing the cost of self-protection increases the rate of safe behavior. Higher reported prevalence also raises the likelihood that individuals would engage in self-protection, where the magnitude of this effect depends on how much time has elapsed in the epidemic. Individuals' experiences in terms of how often an infection was acquired when they did not engage in self-protection are another factor that determines whether they will invest in preventive measures later on. All else being equal, individuals who were infected at a higher rate are more likely to engage in self-protective behavior compared to those with a lower rate of infection. Lastly, fixing everything else, people's willingness to engage in safe behavior waxes or wanes over time, depending on the severity of an epidemic: when prevalence is high, people are more likely to adopt self-protective measures as time goes by; when prevalence is low, a 'self-protection fatigue' effect sets in whereby individuals are less willing to engage in safe behavior over time.

Figure 1. Prevalence of disease and rate of safe behavior in the game.

(a) The fraction of players that were infected in each condition. Using computer simulation results, the short dash line shows the mean prevalence over time if no one ever chooses the safe behavior. The computational model used the same parameter values as the virtual epidemics game and had 50 players, with three chosen to be infected in round 1. The simulations were run 500 times, and the two dash-dot lines indicate 1 standard deviation above and below the mean. (b) The fraction of healthy players that chose the safe action in each condition.

Figure 2. The relationship between prevalence and rate of safe behavior in the following round.

The solid and dash lines are the regression lines for the low and high cost conditions, respectively.

Figure 3. Relationship between prevalence and rate of safe behavior—the effect of the number of rounds elapsed.

The solid lines are the regression lines for the data points from rounds 10 to 26; the dashed lines are the regression lines for the data points from rounds 28 to 44.

Figure 4. Comparing the rate of safe behavior among those whose first action was the risky action to the rate of safe behavior among those whose first action was the safe action.

The “safe” group is composed of those players whose first action was safe. For the low cost condition, there are 13 players in the safe group; for the high cost condition, there are 11 players in the safe group. The “risky” group is composed of those players whose first action was risky. For the low cost condition, there are 38 players in the risky group; for the high cost condition, there are 40 players in the risky group.