In various exemplary embodiments, a system and method for determining a spam post using a spam detection system is presented. The spam detection system receives from the device an image of the item and an item attribute for the item. The spam detection system also extracts the image attributes based on the received image and compares the item attributes to the image attributes. In addition, the spam detection system calculates a confidence score based on the comparison. Furthermore, the spam detection system determines that the item attribute is incorrect based on the confidence score exceeding the predetermined threshold. In response to determining that the item attribute is incorrect, the spam detection system causes the notification to be presented on the display of the device.
展开▼