An individual's responsiveness to targeted content delivery can be affected by a number of factors, such as an interest in the content, other content the user is currently interacting with, the user's current location, or even the time of day. A way of improving targeted content delivery can be to infer a user's current mood and then deliver content that is selected, at least in part, based on the inferred mood. The present technology analyzes mood-associated characteristic data collected over a period of time to produce at least one baseline mood profile for a user. The user's current mood can then be inferred by applying one or more mood rules to compare current mood-associated data to at least one baseline mood profile for the user.