Methods and apparatus for detection of spam publication
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.
1. A method comprising:
receiving, by a detection system from a device, an image of an item for an item listing in an online marketplace;
receiving an item attribute for the item, the item attribute comprising a description of the item inputted by a user on the device;
extracting an image attribute from the image;
comparing, using machine learning, the item attribute comprising the description of the item and the image attribute;
calculating a confidence score based on the comparing, 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;
determining that the item attribute is incorrect based on the confidence score transgressing a first predetermined threshold;
classifying an item publication for the item as spam based on the confidence score transgressing a second predetermined threshold, wherein the second predetermined threshold is different from the first predetermined threshold; and
upon classifying the item publication for the item as spam, removing the item listing.
2. The method of claim 1 , further comprising determining a spam category for the item listing using a rule engine prediction model.
3. The method of claim 2 , wherein the rule engine prediction model is updated based upon information from the item listing.
4. The method of claim 3 , wherein determining the spam category further comprises identifying incorrect information from the item listing.
5. The method of claim 4 , further comprising sending a notification to a user, wherein the notification includes the incorrect information from the item listing.
6. The method of claim 5 , further comprising receiving, in response to sending the notification, corrected information from the user.
7. The method of claim 6 , further comprising, in response to receiving the corrected information, removing the spam category from the item listing.
8. 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 in an online marketplace;
receiving an item attribute for the item, the item attribute comprising a description of the item inputted by a user on the device;
extracting an image attribute from the image;
comparing, using machine learning, the item attribute comprising the description of the item and the image attribute;
calculating a confidence score based on the comparing, 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;
determining that the item attribute is incorrect based on the confidence score transgressing a first predetermined threshold;
classifying an item publication for the item as spam based on the confidence score transgressing a second predetermined threshold, wherein the second predetermined threshold is different from the first predetermined threshold; and
upon classifying the item publication for the item as spam, removing the item listing.
9. The system of claim 8 , wherein the operations further comprise determining a spam category for the item listing using a rule engine prediction model.
10. The system of claim 9 , wherein the rule engine prediction model is updated based upon information from the item listing.
11. The system of claim 10 , wherein determining the spam category further comprises identifying incorrect information from the item listing.
12. The system of claim 11 , wherein the operations further comprise sending a notification to a user, wherein the notification includes the incorrect information from the item listing.
13. The system of claim 12 , wherein the operations further comprise receiving, in response to sending the notification, corrected information from the user.
14. The system of claim 13 , wherein the operations further comprise, in response to receiving the corrected information, removing the spam category from the item listing.
15. 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 in an online marketplace;
receiving an item attribute for the item, the item attribute comprising a description of the item inputted by a user on the device;
extracting an image attribute from the image;
comparing, using machine learning, the item attribute comprising the description of the item and the image attribute;
calculating a confidence score based on the comparing, 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;
determining that the item attribute is incorrect based on the confidence score transgressing a first predetermined threshold;
classifying an item publication for the item as spam based on the confidence score transgressing a second predetermined threshold, wherein the second predetermined threshold is different from the first predetermined threshold; and
upon classifying the item publication for the item as spam, removing the item listing.
16. The non-transitory machine-readable storage medium of claim 15 , wherein the operations further comprise determining a spam category for the item listing using a rule engine prediction model.
17. The non-transitory machine-readable storage medium of claim 16 , wherein determining the spam category further comprises identifying incorrect information from the item listing.
18. The non-transitory machine-readable storage medium of claim 17 , wherein the operations further comprise sending a notification to the user, wherein the notification includes the incorrect information from the item listing.
19. The non-transitory machine-readable storage medium of claim 18 , wherein the operations further comprise receiving, in response to sending the notification, corrected information from the user.
20. The non-transitory machine-readable storage medium of claim 19 , wherein the operations further comprise, in response to receiving the corrected information, removing the spam category from the item listing.