Methods and apparatus for detection of spam publication

Abstract

In various example embodiments, a system and method for determining a spam publication using a spam detection system are presented. The spam detection system receives, from a device, an image of an item and an item attribute for the item. Additionally, the spam detection system extracts an image attribute based on the received image, and compares the item attribute and the image attribute. Moreover, 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 transgressing a predetermined threshold. In response to the determination that the item attribute is incorrect, the spam detection system causes presentation, on a display of the device, of a notification.

What is claimed is: 
     
         1 . A system, comprising:
 at least one processor; and   memory encoding computer-executable instructions that, when executed by the at least one processor, cause the system to perform operations comprising:
 receiving, by a detection system from a device, an image of an item for an item listing; 
 receiving an item attribute for the item, the item attribute including a description of the item inputted by a user on the device; 
 extracting an image attribute from the image; 
 calculating a confidence score based on comparing, using machine learning, the item attribute including the description of the item and the image attribute, the confidence score representing an amount of overlap between the item attribute and the image attribute based on either a basic similarity measure or a machine-learned classifier; 
 comparing the confidence score to one or more threshold values; 
 assigning a rank in an ordered list based on the comparing; and 
 selectively publishing the item listing based on the rank in the ordered list. 
   
     
     
         2 . The system of  claim 1 , wherein the operations further comprise determining that the item attribute is incorrect based on the confidence score satisfying a first threshold value of the one or more threshold values. 
     
     
         3 . The system of  claim 2 , wherein the operations further comprise classifying the item listing as spam based on the confidence score satisfying a second threshold value of the one or more threshold values, the second threshold value different from the first threshold value, wherein selectively publishing the item listing comprises canceling publication of the item listing. 
     
     
         4 . The system of  claim 2 , wherein the operations further comprise:
 classifying the item listing as spam based on the confidence score satisfying a second threshold value of the one or more threshold values, the second threshold value different from the first threshold value; and   demoting the rank of the item listing in the ordered list based on the item attribute being incorrect and the classifying the item listing as spam, wherein selectively publishing the item listing includes publishing the item listing.   
     
     
         5 . The system of  claim 2 , wherein the operations further comprise:
 determining that the confidence score fails to satisfy a second threshold value of the one or more threshold values, the second threshold value different from the first threshold value and indicating a spam status of the item listing; and   demoting the rank of the item listing in the ordered list based on the item attribute being incorrect, wherein selectively publishing the item listing includes publishing the item listing based on the confidence score failing to satisfy the second threshold value.   
     
     
         6 . The system of  claim 2 , wherein the operations further comprise:
 sending a notification indicating that the item attribute is incorrect;   receiving, in response to the notification, a corrected item attribute, a confidence score of the corrected item attribute failing to satisfy the first threshold value; and   promoting the rank of the item listing in the ordered list based on the corrected item attribute, wherein selectively publishing the item listing includes publishing the item listing based on the confidence score of the corrected item attribute failing to satisfy the first threshold value.   
     
     
         7 . The system of  claim 1 , wherein the operations further comprise:
 determining that the item attribute is correct based on the confidence score failing to satisfy a first threshold value of the one or more threshold values; and   promoting the rank of the item listing in the ordered list based on the item attribute being correct, wherein selectively publishing the item listing includes publishing the item listing based on the confidence score failing to satisfy the first threshold value.   
     
     
         8 . The system of  claim 1 , wherein the operations further comprise:
 receiving a search request associated with the item listing; and   presenting, via a user interface, a plurality of item listings including the item listing, respective item listings of the plurality of item listings presented according to a respective rank in the ordered list, wherein the ordered list includes the plurality of item listings.   
     
     
         9 . The system of  claim 8 , wherein the operations further comprise accessing, in response to receiving the search request, a database to obtain the rank in the ordered list. 
     
     
         10 . The system of  claim 1 , wherein the operations further comprise storing the rank in the ordered list in a database. 
     
     
         11 . The system of  claim 1 , wherein the ordered list includes a plurality of item listings including the item listing. 
     
     
         12 . The system of  claim 1 , wherein the item listing comprises at least one of the item attribute or the image of the item. 
     
     
         13 . A method comprising:
 receiving, by a detection system from a device, an image of an item for an item listing;   receiving an item attribute for the item, the item attribute including a description of the item inputted by a user on the device;   extracting an image attribute from the image;   calculating a confidence score based on comparing, using machine learning, the item attribute including the description of the item and the image attribute, the confidence score representing an amount of overlap between the item attribute and the image attribute based on either a basic similarity measure or a machine-learned classifier;   comparing the confidence score to one or more threshold values;   assigning a rank in an ordered list based on the comparing; and   selectively publishing the item listing based on the rank in the ordered list.   
     
     
         14 . The method of  claim 13 , further comprising determining that the item attribute is incorrect based on the confidence score satisfying a first threshold value of the one or more threshold values. 
     
     
         15 . The method of  claim 14 , further comprising classifying the item listing as spam based on the confidence score satisfying a second threshold value of the one or more threshold values, the second threshold value different from the first threshold value, wherein selectively publishing the item listing includes canceling publication of the item listing. 
     
     
         16 . The method of  claim 14 , further comprising:
 determining that the confidence score fails to satisfy a second threshold value of the one or more threshold values, the second threshold value different from the first threshold value and indicating a spam status of the item listing; and   demoting the rank of the item listing in the ordered list based on the item attribute being incorrect, wherein selectively publishing the item listing includes publishing the item listing based on the confidence score failing to satisfy the second threshold value.   
     
     
         17 . The method of  claim 13 , further comprising:
 determining that the item attribute is correct based on the confidence score failing to satisfy a first threshold value of the one or more threshold values; and   promoting the rank of the item listing in the ordered list based on the item attribute being correct, wherein selectively publishing the item listing includes publishing the item listing based on the confidence score failing to satisfy the first threshold value.   
     
     
         18 . A non-transitory machine-readable storage medium comprising instructions that, when executed by at least one processor, cause a system to perform operations comprising:
 receiving, by a detection system from a device, an image of an item for an item listing;   receiving an item attribute for the item, the item attribute including a description of the item inputted by a user on the device;   extracting an image attribute from the image;   calculating a confidence score based on comparing, using machine learning, the item attribute comprising the description of the item and the image attribute, the confidence score representing an amount of overlap between the item attribute and the image attribute based on either a basic similarity measure or a machine-learned classifier;   comparing the confidence score to one or more threshold values;   assigning a rank in an ordered list based on the comparing; and   selectively publishing the item listing based the rank in the ordered list.   
     
     
         19 . The non-transitory machine-readable storage medium of  claim 18 , wherein the operations further comprise determining that the item attribute is incorrect based on the confidence score satisfying a first threshold value of the one or more threshold values. 
     
     
         20 . The non-transitory machine-readable storage medium of  claim 18 , wherein the operations further comprise:
 determining that the item attribute is correct based on the confidence score failing to satisfy a first threshold value of the one or more threshold values; and   promoting the rank of the item listing in the ordered list based on the item attribute being correct, wherein selectively publishing the item listing includes publishing the item listing based on the confidence score failing to satisfy the first threshold value.