A method and system of detecting the activity of “bots” in an online community, by measuring the time elapsed between user actions and comparing this time to a timespan established as normal for users performing the same user actions without the assistance of bots. The timespan may be adjusted when other suspicion characteristics are detected. When detecting actions suspected to be bot-assisted, the method and system respond by executing one or more response instructions against the user suspected of using the bot, with the aim of preventing further bot activity. The response instructions are stored by associating them with a type of user action and a total number of suspect user actions. As a result, the response instructions may be set to increase in severity with each additional suspect act by a user.