There are provided systems and methods for contextual data in augmented reality processing for item recommendations. A first user may provide a recommendation to a second user of an item viewed by the first user through a communication device. The first user may tag the item, for example, through voice input or visual cues while viewing the item at a physical merchant location, or through menu selections within an interface displaying a browsing window of the first user. The first user may provide contextual data that may be used to determine that the first user is recommending the item to the second user, such as voice data that includes an identifier for the second user or visual cues within audiovisual content captured of the item at the physical merchant location. During online browsing, the first user may provide the contextual data through actions, menus selections, and data entry.